© 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. 6807
    Prev
    Next
    INDEX
    Explanations

    end-of-sentence punctuation, formatting

    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
    らの
    0.42
    SPs
    0.40
    たちの
    0.39
    …).
    0.37
    ...";
    0.36
    țele
    0.35
    子の
    0.35
    ကုန်
    0.35
    性和
    0.35
    τρέ
    0.33
    POSITIVE LOGITS
    ؟
    0.45
    ）
    0.44
    ">
    0.42
     []
    0.42
    ```
    0.41
    ()
    0.41
    ‬
    0.40
     :
    0.39
    ":
    0.39
    ))
    0.39
    Activations Density 0.154%

    No Known Activations