© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 261
    Prev
    Next
    INDEX
    Explanations

    social interaction discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    0
    1.80
    ০০
    1.70
     haven
    1.61
    I
    1.50
     rest
    1.43
    ০
    1.42
     don
    1.41
     didn
    1.41
     grass
    1.39
    层面
    1.39
    POSITIVE LOGITS
    ки
    1.70
    and
    1.65
    ž
    1.63
    ва
    1.61
    Liens
    1.59
     efectivos
    1.50
    𒁹
    1.48
    ное
    1.48
     деву
    1.48
     Bartholom
    1.48
    Activations Density 0.102%

    No Known Activations