© 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. 100644
    Prev
    Next
    INDEX
    Explanations

    except DOA, a table, other Cam, a title, and youth, detract from, development of, other properties

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

    conversions, decisions, putting

    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
    tml
    0.46
    がなく
    0.45
    animate
    0.44
    duk
    0.44
    kuu
    0.43
    &
    0.41
     চলুন
    0.41
    ubert
    0.41
    xx
    0.40
    ONU
    0.40
    POSITIVE LOGITS
    ยาก
    0.50
     края
    0.49
    नल
    0.49
     openc
    0.48
    áli
    0.47
    不易
    0.46
    髋
    0.46
    屐
    0.45
    ামত
    0.45
    瞌
    0.44
    Activations Density 0.001%

    No Known Activations