© 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. 39787
    Prev
    Next
    INDEX
    Explanations

    making gains

    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
     “
    -2.30
    ”,
    -2.14
    ?”
    -2.11
    —“
    -2.08
     Это
    -2.05
     …”
    -1.92
     a
    -1.90
    0
    -1.87
    on
    -1.85
    ...”
    -1.83
    POSITIVE LOGITS
    genodigd
    2.80
    ꙰
    2.42
    犼
    2.38
    Ꮫ
    2.17
    饪
    2.02
     皮肤
    1.98
     菲
    1.98
    ଝ
    1.97
    rogels
    1.97
    禟
    1.94
    Activations Density 0.010%

    No Known Activations