© 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. 26595
    Prev
    Next
    INDEX
    Explanations

    fallback value or default option

    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
     descubrió
    -1.18
     advierte
    -1.05
    hibitions
    -0.97
    cosplay
    -0.95
    锹
    -0.92
    นะนำ
    -0.91
     RECOMMEND
    -0.90
    donna
    -0.90
     quadrinhos
    -0.90
    を発見
    -0.89
    POSITIVE LOGITS
     if
    1.25
     defaultValue
    1.13
    defaultValue
    1.12
     value
    1.09
     option
    1.06
     alternative
    1.05
     replacement
    1.03
     result
    1.03
     substitute
    1.03
     fallback
    1.02
    Activations Density 0.026%

    No Known Activations