© 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. 38567
    Prev
    Next
    INDEX
    Explanations

    linear functions

    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
     [...
    1.18
     روشنی
    1.07
     चलकर
    1.05
     χρησιμοποι
    1.04
     misfit
    0.99
    쥐
    0.98
     consign
    0.97
     গিয়ে
    0.96
    ००
    0.96
     crem
    0.95
    POSITIVE LOGITS
    i
    1.59
    している
    1.34
    č
    1.31
    ਤਾ
    1.24
    ve
    1.23
    ه
    1.23
    abouts
    1.23
    ة
    1.21
    }$$
    1.20
    يث
    1.19
    Activations Density 0.002%

    No Known Activations