© 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. 22-GEMMASCOPE-RES-131K
    7. 64761
    Prev
    Next
    INDEX
    Explanations

    names and specific words

    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
     We
    -2.61
    \
    -2.50
     if
    -2.34
    .,
    -2.30
     The
    -2.16
     morire
    -2.13
    Then
    -2.11
    There
    -2.08
     Here
    -2.06
    Because
    -2.06
    POSITIVE LOGITS
    to
    2.88
    蝋
    2.61
    鮓
    2.28
    
    2.25
    逦
    2.22
    琑
    2.22
    and
    2.19
    獁
    2.19
    aaaa
    2.17
    aaa
    2.17
    Activations Density 0.165%

    No Known Activations