© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1376
    Prev
    Next
    INDEX
    Explanations

    pronouns and subject matter

    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
    い
    1.27
    5
    1.20
    തിന്
    1.14
     Ac
    1.13
    4
    1.13
    ामध्ये
    1.13
    6
    1.13
    com
    1.12
    ेत
    1.10
    3
    1.10
    POSITIVE LOGITS
    ్యాచ్
    1.23
     resetCounters
    1.16
    ೃಷ್ಣ
    1.12
     الحلقه
    1.10
     roky
    1.10
     elettron
    1.09
    К
    1.08
     работал
    1.05
    Компания
    1.05
    こと
    1.04
    Activations Density 0.133%

    No Known Activations