© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31050
    Prev
    Next
    INDEX
    Explanations

    monument valley

    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
     vết
    1.36
    ر
    1.25
    ี่ยน
    1.14
    uya
    1.12
     sportsman
    1.09
     fréqu
    1.00
    痠
    0.99
     syringe
    0.98
    ен
    0.97
    er
    0.96
    POSITIVE LOGITS
    س
    1.61
    {$
    1.48
    𝘳
    1.41
    ara
    1.40
    Show
    1.40
    ā
    1.38
     Résultats
    1.34
    Regards
    1.33
    ies
    1.30
    م
    1.30
    Activations Density 0.000%

    No Known Activations