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

    Neuronpedia

    Jacobian LensNEW
    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. 42376
    Prev
    Next
    INDEX
    Explanations

    digital micromirror devices, APUs, traps, rear coating, dating sim, environment, IDEs, braking ratio

    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
    it
    1.80
    ной
    1.55
    ள்ளது
    1.48
     cercano
    1.46
     pertenec
    1.45
    ’
    1.45
     previo
    1.44
    That
    1.41
     זאת
    1.35
    '
    1.34
    POSITIVE LOGITS
    ु
    1.58
    ো
    1.57
    ी
    1.45
    ه
    1.42
    ش
    1.42
    স
    1.41
     Melanes
    1.41
    क
    1.40
     Tübingen
    1.35
    ש
    1.35
    Activations Density 0.000%

    No Known Activations