© 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. 38104
    Prev
    Next
    INDEX
    Explanations

    hypersensitivity, fewest, deeply, experienced, lowest, dependent, allergies

    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
    ة
    0.93
    ード
    0.91
    션
    0.88
    setVerticalGroup
    0.86
    ير
    0.85
     Kabel
    0.84
     Официа
    0.84
     Fonds
    0.83
     क्रिस
    0.82
    لف
    0.81
    POSITIVE LOGITS
    面
    0.73
     quer
    0.72
     compromet
    0.69
     mọi
    0.68
     activ
    0.66
     server
    0.66
     গিয়ে
    0.65
     রাজপ
    0.65
    ernet
    0.64
    entially
    0.64
    Activations Density 0.000%

    No Known Activations