© 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. 21363
    Prev
    Next
    INDEX
    Explanations

    words describing habitation

    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
    𝄆
    -2.58
    荜
    -2.30
    antaine
    -2.27
    鐿
    -2.20
    蓥
    -2.16
     herr
    -2.13
     projets
    -1.97
    岽
    -1.93
    didSet
    -1.91
    ￬
    -1.91
    POSITIVE LOGITS
    er
    2.86
    1
    2.77
     -
    2.58
    h
    2.58
    t
    2.52
    ه
    2.52
    nt
    2.38
    .,
    2.36
     segítség
    2.31
    ers
    2.28
    Activations Density 0.002%

    No Known Activations