© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19725
    Prev
    Next
    INDEX
    Explanations

    abstract concepts across languages

    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_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
     Cómo
    0.66
    旖
    0.62
    $，
    0.60
    intersection
    0.59
    ₂,
    0.59
    })$,
    0.59
    }$,
    0.59
    \}$,
    0.59
     Schad
    0.59
    ራል
    0.58
    POSITIVE LOGITS
    ্তির
    0.61
    表現
    0.58
    ຂອງທ່ານ
    0.58
     employed
    0.58
    的东西
    0.57
    ের
    0.57
     granted
    0.56
     noteworthy
    0.56
     declarado
    0.56
    ของ
    0.56
    Activations Density 0.082%

    No Known Activations