© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    resilience

    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
    тность
    2.16
    
    2.03
    นี้
    1.91
    ⓡ
    1.88
     llamar
    1.87
    在
    1.87
    ले
    1.86
     abstinence
    1.85
    冶
    1.85
    ти
    1.82
    POSITIVE LOGITS
    m
    2.27
    a
    2.17
    é
    1.80
    ق
    1.79
    ut
    1.72
    id
    1.71
    ind
    1.70
    ens
    1.67
    ic
    1.62
    and
    1.62
    Activations Density 0.020%

    No Known Activations