© 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. 10-GEMMASCOPE-RES-131K
    7. 13938
    Prev
    Next
    INDEX
    Explanations

    FX and inheritance

    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_10/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
    蜴
    -3.02
    of
    -2.59
     ſy
    -2.53
    橚
    -2.50
    ی
    -2.47
    民宿
    -2.44
    踽
    -2.42
    <bos>
    -2.42
    廨
    -2.38
    禤
    -2.34
    POSITIVE LOGITS
     We
    3.45
     són
    2.56
     I
    2.56
    ᡴ
    2.44
     Now
    2.44
     Our
    2.38
    e
    2.36
     zwei
    2.28
     bahwa
    2.28
     And
    2.25
    Activations Density 0.004%

    No Known Activations