© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4876
    Prev
    Next
    INDEX
    Explanations

    return and raise descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     অস্ট্র
    0.53
    électricité
    0.51
    ൂ
    0.50
    autom
    0.50
     penile
    0.50
     totiž
    0.50
     اهو
    0.50
     zuk
    0.49
    servlet
    0.49
    }^{(
    0.49
    POSITIVE LOGITS
     Notes
    0.51
    ————————————————
    0.51
    <h2>
    0.50
     caveats
    0.48
    .”)
    0.48
    ----------------
    0.47
    ________________
    0.46
    Referensi
    0.46
     NOTES
    0.46
     endregion
    0.45
    Activations Density 0.216%

    No Known Activations