© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105303
    Prev
    Next
    INDEX
    Explanations

    paths and trajectories

    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
     berdua
    -1.62
    ?」
    -1.58
    atization
    -1.57
    粜
    -1.56
    atized
    -1.56
    镲
    -1.54
    umerable
    -1.47
    ulence
    -1.46
     truk
    -1.45
    bernador
    -1.40
    POSITIVE LOGITS
    -
    1.63
     he
    1.59
     At
    1.58
     path
    1.53
    —
    1.48
    '
    1.40
     bekämp
    1.38
     my
    1.38
     Или
    1.34
     These
    1.31
    Activations Density 0.066%

    No Known Activations