© 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. 19931
    Prev
    Next
    INDEX
    Explanations

    assimilation, similar, Asimov, Asim Omar

    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
    ｉ
    -2.42
    -2.41
    )」
    -2.30
     naszego
    -2.23
    制的
    -2.17
     इसकी
    -2.09
     impetus
    -2.08
     sociala
    -2.06
     insanity
    -2.03
     blueberry
    -2.03
    POSITIVE LOGITS
     rebellious
    2.20
    {
    1.99
    何故
    1.99
    のほうが
    1.96
     tecn
    1.88
    iques
    1.84
    éviter
    1.83
    ”
    1.83
    喾
    1.80
     He
    1.80
    Activations Density 0.004%

    No Known Activations