© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    highest precision

    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
    as
    0.63
    u
    0.63
     to
    0.58
    to
    0.54
    ff
    0.53
     Accounting
    0.51
    nd
    0.50
     into
    0.49
     Transportation
    0.48
     Ayam
    0.48
    POSITIVE LOGITS
    ろし
    0.54
    γει
    0.50
    ฐาน
    0.46
    Му
    0.45
    อย
    0.45
    ਟ
    0.44
    гах
    0.44
     kolom
    0.44
    ዻ
    0.44
    फोन
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.