© 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. 6107
    Prev
    Next
    INDEX
    Explanations

    hearing or heard

    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
    a
    2.09
    ی
    2.03
    '
    1.92
     tumors
    1.87
     savor
    1.86
    های
    1.84
     endeav
    1.83
     analyze
    1.77
     odors
    1.77
    ulate
    1.74
    POSITIVE LOGITS
    ర్
    2.23
    ர்
    1.86
    ン
    1.60
     téléphonique
    1.57
    ávan
    1.55
    蝌
    1.48
    ácia
    1.48
    KURZ
    1.47
    龈
    1.47
     lâng
    1.45
    Activations Density 0.009%

    No Known Activations