© 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. 30975
    Prev
    Next
    INDEX
    Explanations

    of thein programming

    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
    V
    1.11
    P
    1.06
     V
    1.05
     Un
    1.04
     Sub
    0.97
     When
    0.97
     Under
    0.96
     There
    0.96
     Once
    0.95
     Muster
    0.95
    POSITIVE LOGITS
    tobago
    1.13
    Ⴉ
    1.06
    둴
    1.06
     ignoreString
    1.05
    न्त्री
    1.04
     unglaublich
    1.04
     സെക്ര
    1.03
     alot
    1.02
    iences
    1.01
     esperti
    1.01
    Activations Density 0.000%

    No Known Activations