© 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. 7965
    Prev
    Next
    INDEX
    Explanations

    layout and view creation

    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
    ↵
    -3.44
     ۵
    -2.53
    Ꮞ
    -2.14
    𒊹
    -2.13
     был
    -2.08
    皤
    -2.06
    ᯾
    -2.06
    肫
    -2.03
    0
    -2.03
    优秀
    -2.03
    POSITIVE LOGITS
    ].
    3.02
    on
    2.78
     was
    2.52
    it
    2.44
    )
    2.34
    We
    2.33
     Like
    2.33
    I
    2.28
     selben
    2.25
    nienia
    2.23
    Activations Density 0.001%

    No Known Activations