© 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. 22-GEMMASCOPE-RES-131K
    7. 67058
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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_22/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
     when
    -1.15
    When
    -1.09
    iją
    -1.03
     antichi
    -1.02
     does
    -1.00
    If
    -0.98
     }(
    -0.98
     familias
    -0.97
    :^{
    -0.95
     oración
    -0.94
    POSITIVE LOGITS
     insides
    1.02
    わざわざ
    1.00
     erhi
    0.98
     jim
    0.97
     différents
    0.96
     charlotte
    0.96
     horrifying
    0.94
     incompar
    0.94
    十分的
    0.94
     своим
    0.93
    Activations Density 0.001%

    No Known Activations