© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30376
    Prev
    Next
    INDEX
    Explanations

    Precedential, Prettl, precomp

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    тной
    -0.87
    ረ
    -0.82
    潼
    -0.80
     seleccione
    -0.79
    Dziękuję
    -0.79
     Assim
    -0.77
     prevailed
    -0.77
     pensare
    -0.76
     minori
    -0.76
    ാന
    -0.75
    POSITIVE LOGITS
     Pre
    1.06
    Pre
    0.90
     pre
    0.89
    预
    0.85
     プレ
    0.79
     пред
    0.78
     kwamba
    0.78
    PROBE
    0.73
    PRE
    0.72
    白色
    0.72
    Activations Density 0.081%

    No Known Activations