© 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. 22-GEMMASCOPE-RES-131K
    7. 66233
    Prev
    Next
    INDEX
    Explanations

    headings, code, or dates

    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_22/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
     таке
    -1.23
    J
    -1.22
    P
    -1.17
    E
    -1.14
    F
    -1.11
    ａ
    -1.09
    U
    -1.08
    K
    -1.06
     せ
    -1.05
    fiore
    -1.05
    POSITIVE LOGITS
     australiano
    1.23
    哢
    1.22
    百貨
    1.18
    splitContainer
    1.16
    Sommaire
    1.16
     two
    1.15
    Ruj
    1.13
    Spesifikasi
    1.12
    tembre
    1.09
     enfrentan
    1.08
    Activations Density 0.010%

    No Known Activations