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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67685
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     soooo
    -1.53
     alcune
    -1.53
     strikingly
    -1.51
     dando
    -1.49
     alguns
    -1.49
     revamped
    -1.41
     momentous
    -1.41
     verschillende
    -1.41
     sooo
    -1.38
     vários
    -1.35
    POSITIVE LOGITS
     at
    1.81
     their
    1.77
     continual
    1.45
     in
    1.41
     considerable
    1.40
     extraordinarily
    1.40
     with
    1.39
     from
    1.38
     what
    1.36
     sizable
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.