© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112293
    Prev
    Next
    INDEX
    Explanations

    embedding files or resources

    np_acts-logits-general · gemini-2.5-flash-lite

    the verb "embed" and its variations (embedded, embedding) in technical or instructional contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     he
    -2.61
    .
    -2.58
    🫃
    -2.44
    瓩
    -2.28
    颪
    -2.17
    骉
    -2.11
    ☑️
    -2.08
    ￬
    -2.08
    塤
    -2.05
    鸝
    -2.03
    POSITIVE LOGITS
    賔
    2.14
    ⦊
    2.13
    ଃ
    2.08
    𖥦
    2.06
    現在は
    2.03
    jaqueta
    1.99
    s
    1.95
    </strong>
    1.95
     высоким
    1.90
    geſ
    1.86
    Activations Density 0.015%

    No Known Activations