© 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. 25098
    Prev
    Next
    INDEX
    Explanations

    copy, match, change, stick

    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
     ponieważ
    0.52
    ترى
    0.50
     réseau
    0.44
    䡇
    0.43
    攻击
    0.43
     Desire
    0.42
     ağı
    0.42
     embryonic
    0.42
     Netzwerk
    0.41
    続けて
    0.41
    POSITIVE LOGITS
    ｸ
    0.44
    havam
    0.43
    ','
    0.43
     variado
    0.43
     convicts
    0.42
     Constable
    0.42
    จุ
    0.41
     shēng
    0.41
     lowland
    0.41
    oughs
    0.40
    Activations Density 0.001%

    No Known Activations