© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    names ending in an or an otta

    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_65k_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
    츰
    0.24
    ပြု
    0.21
    marshalN
    0.21
     ഇത്
    0.21
    约翰
    0.20
     χρήση
    0.20
     λί
    0.20
     διαδικ
    0.20
    เสียหาย
    0.20
     διαφορε
    0.20
    POSITIVE LOGITS
    es
    0.23
    d
    0.22
     obtained
    0.22
    i
    0.22
    ul
    0.22
    en
    0.21
    ic
    0.21
     were
    0.21
    u
    0.21
    ik
    0.21
    Activations Density 0.012%

    No Known Activations