© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62217
    Prev
    Next
    INDEX
    Explanations

    availability, measurement, demolition

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

    Spanish and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    0.58
     claim
    0.57
    /
    0.56
     R
    0.55
     Rose
    0.55
    !
    0.54
     PM
    0.54
     Common
    0.52
    ,
    0.52
     x
    0.51
    POSITIVE LOGITS
    ufieurs
    0.59
    bindingFields
    0.59
    cartes
    0.57
     ወቅት
    0.57
    ੀ
    0.56
    igheten
    0.56
    piej
    0.55
     ሁለት
    0.55
     সমাধ
    0.54
    countery
    0.54
    Activations Density 0.000%

    No Known Activations