© 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. 44331
    Prev
    Next
    INDEX
    Explanations

    days, throughout, details, internationally, valid

    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
    𝒐
    0.82
     δικ
    0.80
     اتارنا
    0.79
    ChooseCharacter
    0.79
     tecnologie
    0.79
    neutrophiles
    0.78
     conclusione
    0.78
     scienze
    0.77
    <0xA9>
    0.76
    เข
    0.76
    POSITIVE LOGITS
    it
    1.02
    сной
    0.81
    lia
    0.80
     elemental
    0.80
    ']:
    0.79
    ox
    0.78
    ет
    0.77
    суа
    0.77
    ։
    0.77
    ig
    0.77
    Activations Density 0.000%

    No Known Activations