© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138343
    Prev
    Next
    INDEX
    Explanations

    dominican, volcanic, knowledge, vegan

    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_16_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
    i
    0.54
    ed
    0.46
    ї
    0.44
    し
    0.44
     contrived
    0.43
    通り
    0.42
    obie
    0.41
    driver
    0.40
    abilit
    0.40
    י
    0.40
    POSITIVE LOGITS
     vermelho
    0.51
    뚠
    0.49
    كتور
    0.49
     CCOC
    0.49
     Ull
    0.47
    ご注意
    0.47
     ఒక
    0.47
    iteurs
    0.47
     Dmitri
    0.46
     مست
    0.46
    Activations Density 0.000%

    No Known Activations