© 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. 131459
    Prev
    Next
    INDEX
    Explanations

    posters about, love watching, extended interview, car hire

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

    sex, randomness, queues, and full features

    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
    ور
    0.45
    res
    0.43
    itus
    0.43
    itum
    0.43
    pc
    0.43
    I
    0.43
    다
    0.43
    op
    0.42
    pattern
    0.42
    लोक
    0.41
    POSITIVE LOGITS
     proizvođa
    0.62
     llev
    0.59
     beginnetje
    0.56
     hydrogenation
    0.53
     llevaba
    0.53
     विक्रेता
    0.53
     vudd
    0.52
     вас
    0.52
     bassa
    0.52
     ကျွန်
    0.52
    Activations Density 0.001%

    No Known Activations