© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8430
    Prev
    Next
    INDEX
    Explanations

    explanation starter "1."

    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
    రీలు
    0.92
    ations
    0.92
    purpose
    0.86
    "};
    0.84
     purpose
    0.83
    Rationale
    0.83
    מים
    0.80
     };
    0.78
     }\
    0.77
    er
    0.77
    POSITIVE LOGITS
     Turned
    0.97
     Effectively
    0.95
     получилось
    0.94
     الى
    0.92
    𝙏
    0.92
    bodyParser
    0.87
     को
    0.86
     essentially
    0.86
     emphatically
    0.86
     essentiellement
    0.86
    Activations Density 0.129%

    No Known Activations