© 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. 38638
    Prev
    Next
    INDEX
    Explanations

    swear or promise

    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
    ن
    1.46
    m
    1.16
     ameryka
    0.99
     sieci
    0.99
     exempel
    0.98
     podía
    0.96
     Entretanto
    0.96
    न
    0.96
     pourraient
    0.95
    م
    0.95
    POSITIVE LOGITS
    heses
    1.20
     intruder
    1.07
    Ꮷ
    1.07
    фии
    1.05
    да
    1.04
    )$\\
    1.03
    glBind
    1.02
    imony
    1.02
    iteli
    1.01
    ্জ
    1.00
    Activations Density 0.001%

    No Known Activations