© 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. 17338
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives in parentheses

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

    qualified 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
     which
    0.59
    which
    0.48
     projectiles
    0.44
     installations
    0.44
     the
    0.43
    This
    0.41
     পাকিস্তানীরা
    0.41
    를
    0.40
     is
    0.40
     notepad
    0.40
    POSITIVE LOGITS
     (?)
    0.49
    (?)
    0.49
    (?
    0.46
    -)
    0.46
    (!)
    0.46
     także
    0.45
    쿵
    0.45
     (!)
    0.45
    followlike
    0.44
    <0xC9>
    0.44
    Activations Density 0.068%

    No Known Activations