© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3104
    Prev
    Next
    INDEX
    Explanations

    imagine a hypothetical scenario

    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
     Η
    1.56
     fragrance
    1.41
    ][/
    1.39
     pH
    1.32
    ت
    1.32
    TY
    1.31
    +"
    1.29
     decidedly
    1.28
    1.22
    ɳ
    1.20
    POSITIVE LOGITS
    ش
    1.89
    स्पति
    1.80
    ⺆
    1.70
    น
    1.68
    ET
    1.66
    nél
    1.66
    াযোগ
    1.64
    áme
    1.63
    ம்
    1.59
    e
    1.56
    Activations Density 0.010%

    No Known Activations