© 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. 24-GEMMASCOPE-2-RES-262K
    7. 7487
    Prev
    Next
    INDEX
    Explanations

    sequences and calculations

    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_24_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
    níka
    0.65
    Для
    0.61
    ᾧ
    0.59
    ciato
    0.59
    ।...
    0.57
    õ
    0.57
    Ἠ
    0.57
    acariy
    0.56
    ("");
    0.55
    ᓛ
    0.55
    POSITIVE LOGITS
     valamint
    0.84
     மற்றும்
    0.82
     F
    0.79
     ,
    0.79
    、、
    0.79
     illetve
    0.79
     、
    0.75
     P
    0.73
     J
    0.73
    、
    0.72
    Activations Density 0.022%

    No Known Activations