© 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. 107185
    Prev
    Next
    INDEX
    Explanations

    see how or what

    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
    们的
    -1.29
    可以说是
    -1.20
     ა
    -1.16
    雳
    -1.16
    sigen
    -1.15
    appcompat
    -1.13
    毡
    -1.13
     EXAMINATION
    -1.12
     Acest
    -1.10
    呖
    -1.10
    POSITIVE LOGITS
     how
    2.88
     firsthand
    2.31
     what
    2.05
     glimpses
    1.69
     them
    1.60
     where
    1.60
     the
    1.59
     something
    1.38
     why
    1.35
     some
    1.34
    Activations Density 0.037%

    No Known Activations