© 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. 169495
    Prev
    Next
    INDEX
    Explanations

    indemnify, Teams, physician, check

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

    meeting points, primes, retaliation, size, palindromes

    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
    alon
    0.50
    </h1>
    0.44
    ris
    0.44
    wah
    0.44
    job
    0.41
     गुलाम
    0.41
    warehouse
    0.41
    chore
    0.41
    icked
    0.40
     بچه
    0.40
    POSITIVE LOGITS
     Köln
    0.48
    匪
    0.48
     İz
    0.47
     Begegn
    0.47
     dieser
    0.47
     außergewöhn
    0.47
     phổi
    0.46
    യില്ല
    0.46
    лети
    0.46
     assure
    0.46
    Activations Density 0.000%

    No Known Activations