© 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-262K
    7. 71433
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

    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
    𝗼
    0.47
    気温
    0.45
    Tmp
    0.45
    onycha
    0.45
     TEMP
    0.44
     adjour
    0.43
    ons
    0.43
    ULTURAL
    0.43
    он
    0.43
    量は
    0.43
    POSITIVE LOGITS
    潛行
    0.50
     🙏
    0.48
     '}
    0.47
     Discourse
    0.44
     bliver
    0.43
     Pip
    0.43
     hjæl
    0.42
    fNil
    0.42
     ibang
    0.42
     laut
    0.41
    Activations Density 0.004%

    No Known Activations