© 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. 1321
    Prev
    Next
    INDEX
    Explanations

    torsion phenomena

    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
    utente
    1.09
    ส์
    1.08
    с
    1.08
    u
    1.06
    Bars
    1.02
    ান্তরিত
    1.02
    čili
    1.01
    I
    1.01
    uksen
    0.99
    Time
    0.99
    POSITIVE LOGITS
     plow
    1.22
     plough
    1.05
     chipset
    1.04
     mnog
    0.99
     Anfield
    0.98
     hatch
    0.96
     reprieve
    0.96
     mop
    0.95
     tornado
    0.95
     extinguishers
    0.95
    Activations Density 0.000%

    No Known Activations