© 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
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241371
    Prev
    Next
    INDEX
    Explanations

    drawing canvas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subnet
    0.60
     patriots
    0.55
    醇
    0.55
    brero
    0.54
    urangan
    0.54
    appers
    0.52
     сете
    0.52
    Akt
    0.52
     racers
    0.52
     ससुराल
    0.52
    POSITIVE LOGITS
    ENSION
    0.57
     relatos
    0.54
    ကျွန်
    0.51
     jornalista
    0.51
     ကျွန်
    0.51
    憎
    0.50
    കെ
    0.50
    唱歌
    0.50
    જે
    0.49
     tensão
    0.48
    Activations Density 0.000%

    No Known Activations