© 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. 31039
    Prev
    Next
    INDEX
    Explanations

    projection

    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
    ע
    2.48
    ের
    2.05
    ن
    2.00
    து
    1.96
    कृष्ण
    1.93
    ार
    1.90
    র
    1.88
    ня
    1.88
    три
    1.84
    ar
    1.83
    POSITIVE LOGITS
     وبعد
    1.78
    ct
    1.72
    ij
    1.70
    ro
    1.67
    ii
    1.66
    it
    1.66
    ff
    1.63
    ppure
    1.63
    ⏤
    1.61
    den
    1.59
    Activations Density 0.005%

    No Known Activations