© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 212590
    Prev
    Next
    INDEX
    Explanations

    invention disclosures, bending rock, on August

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

    maintaining, good at, provide an, aim to

    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
    ienia
    0.56
     סי
    0.54
     גי
    0.54
     農
    0.53
     Фурга
    0.50
     व्यू
    0.49
    iry
    0.48
    arlı
    0.48
     פרו
    0.47
     הר
    0.47
    POSITIVE LOGITS
    a
    0.54
    h
    0.52
    해야
    0.51
    ه
    0.50
    an
    0.48
    з
    0.47
     realizada
    0.46
     primed
    0.46
    х
    0.46
     próxima
    0.46
    Activations Density 0.001%

    No Known Activations