© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    list context or topic

    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
     a
    0.63
     an
    0.53
     the
    0.52
     а
    0.50
    +](=
    0.46
    Ა
    0.43
    ود
    0.42
    зывают
    0.42
    ClrBit
    0.42
     dilapidated
    0.40
    POSITIVE LOGITS
    .)
    0.52
     поскольку
    0.52
    ‌.
    0.52
     oraz
    0.50
     konusunda
    0.50
    .
    0.50
     sowie
    0.49
    .”
    0.49
     dahil
    0.48
     -
    0.47
    Activations Density 0.161%

    No Known Activations