© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108594
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on template‐ or server‐side code injection points—things like include directives, interpolation tags (e.g. {{…}} or {%…%}), Response.Write calls, ng-bind/html attributes, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irà
    -0.79
    导
    -0.78
    ɵɵelementEnd
    -0.77
     vpon
    -0.71
    彳
    -0.71
     forState
    -0.70
    ,«
    -0.69
     francês
    -0.68
     sendiri
    -0.68
     walked
    -0.68
    POSITIVE LOGITS
     وليس
    0.78
    いが
    0.77
    '}}>
    0.75
     contiennent
    0.75
    Restrictions
    0.74
     compét
    0.73
     mắn
    0.73
    ക്ഷ
    0.73
     našich
    0.72
    KURZBESCHREIBUNG
    0.72
    Activations Density 0.003%

    No Known Activations