© 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. 59153
    Prev
    Next
    INDEX
    Explanations

    unordered list (`ul`)

    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
     we
    -2.20
     and
    -1.97
    совой
    -1.87
    を見た
    -1.81
    bbbb
    -1.80
     to
    -1.75
    спомина
    -1.74
     Aussehen
    -1.69
    眥
    -1.67
     en
    -1.64
    POSITIVE LOGITS
    ᐕ
    2.41
    3
    2.14
    .=
    2.09
    ஂ
    2.06
     kostenlose
    2.06
    鵯
    2.06
    8
    2.05
    很棒
    2.03
    卧槽
    2.03
    嵓
    2.02
    Activations Density 0.002%

    No Known Activations