© 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. 202552
    Prev
    Next
    INDEX
    Explanations

    higher than, smart city, serving employee

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

    models and specific descriptions

    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
    স্কার
    0.58
    czenia
    0.53
    itabbo
    0.52
     যাওয়া
    0.51
    ctype
    0.51
    mature
    0.50
    FBSDKInternal
    0.50
    骶
    0.50
    numerator
    0.50
    篮球
    0.49
    POSITIVE LOGITS
     as
    0.55
     rich
    0.48
     liquefied
    0.46
     maestros
    0.45
     hudson
    0.45
    ↵
    0.45
     fond
    0.44
     the
    0.44
     ai
    0.44
     Fond
    0.44
    Activations Density 0.000%

    No Known Activations