© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24378
    Prev
    Next
    INDEX
    Explanations

    -able or -nable words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    прода
    0.73
    рующих
    0.65
    판매
    0.62
    𒉡
    0.62
    ing
    0.62
    ро
    0.62
    revise
    0.59
    ிருஷ்
    0.59
     relatifs
    0.59
    それ
    0.59
    POSITIVE LOGITS
    যোগ্য
    0.79
    able
    0.76
    ABLE
    0.63
    izable
    0.55
     workable
    0.55
     d
    0.55
    ao
    0.55
    는
    0.55
    dır
    0.55
    是
    0.55
    Activations Density 0.130%

    No Known Activations