© 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
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15223
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺃ
    0.62
    }}}
    0.60
    }}}}
    0.57
    {}".
    0.57
    ໄດ້
    0.57
    ≤
    0.57
    )}},
    0.55
    (($
    0.54
     उन्नत
    0.53
    (`<
    0.53
    POSITIVE LOGITS
     Args
    0.70
     তিনটি
    0.65
     চারটি
    0.63
     includes
    0.61
     दो
    0.59
    얹
    0.59
     incluir
    0.59
    Includes
    0.58
    istles
    0.58
     Includes
    0.57
    Activations Density 0.000%

    No Known Activations