© 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. 83981
    Prev
    Next
    INDEX
    Explanations

    introduces descriptive phrase or choice

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

    enabled knowledge, capabilities, algorithm, sold, transport, city, illness

    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
    ؑ
    0.44
     দায়ী
    0.43
    Đáp
    0.41
     bathrooms
    0.40
     ':'
    0.40
    Czy
    0.39
    ką
    0.38
    もある
    0.38
     शुभार
    0.38
    爵
    0.38
    POSITIVE LOGITS
    id
    0.54
    ell
    0.53
     amplitud
    0.49
    is
    0.48
    as
    0.48
    ou
    0.48
    um
    0.48
    ris
    0.48
    osz
    0.46
    j
    0.46
    Activations Density 0.000%

    No Known Activations