© 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. 22-GEMMASCOPE-RES-131K
    7. 15354
    Prev
    Next
    INDEX
    Explanations

    motors, node, males, holes, density

    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
     or
    -1.34
    öbb
    -1.17
     may
    -1.10
    colage
    -1.09
    dillera
    -1.08
     suggests
    -1.06
    ỹ
    -1.05
    inetto
    -1.05
    icata
    -1.03
     ativar
    -1.02
    POSITIVE LOGITS
     kado
    1.48
     hant
    1.48
     plafon
    1.43
     traktor
    1.38
     hala
    1.37
     pê
    1.36
     patro
    1.35
     krim
    1.34
    𓆏
    1.34
     empat
    1.33
    Activations Density 0.026%

    No Known Activations