© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    NA, Na, or Nah

    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
    𝗺
    2.00
     accéder
    1.88
    ١
    1.88
    t
    1.88
     jaunes
    1.87
     Agustus
    1.82
     únic
    1.80
    ์
    1.76
    iada
    1.70
     Establish
    1.69
    POSITIVE LOGITS
    یت
    2.69
    да
    2.66
    ų
    2.47
    서
    2.44
    িল
    2.39
    ير
    2.38
    iciente
    2.30
    ación
    2.20
    Ꮀ
    2.11
    ्री
    2.09
    Activations Density 0.030%

    No Known Activations