© 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. 38995
    Prev
    Next
    INDEX
    Explanations

    past habits or states

    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
    4
    -2.81
    0
    -2.47
    9
    -2.22
    3
    -2.19
    6
    -2.14
     that
    -2.14
    8
    -2.13
    ↵↵
    -2.06
    7
    -2.03
    他的
    -1.92
    POSITIVE LOGITS
    𝑛
    1.96
    biendo
    1.94
    📩
    1.69
    钝
    1.67
    wachsenen
    1.62
     be
    1.59
    紺
    1.59
    gså
    1.54
    関する
    1.53
    siębior
    1.53
    Activations Density 0.008%

    No Known Activations