© 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. 21149
    Prev
    Next
    INDEX
    Explanations

    of four, and at, much like, good fight, a strain, a buck

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

    Some jobs, stations, data

    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
    apia
    0.49
    ه
    0.49
    Arte
    0.48
    site
    0.48
    July
    0.46
    t
    0.46
    i
    0.46
    sol
    0.46
    y
    0.46
    Bern
    0.46
    POSITIVE LOGITS
     sikker
    0.47
     réseaux
    0.46
     อนุ
    0.46
     mismas
    0.46
     hátsó
    0.45
     säker
    0.45
     réelle
    0.45
     มือ
    0.44
     swojej
    0.44
     অনুমতি
    0.44
    Activations Density 0.000%

    No Known Activations