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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7098
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions and states

    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_16k_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
     według
    0.79
     sebagaimana
    0.78
    （
    0.77
     according
    0.77
     cosidd
    0.77
     multimillion
    0.77
    めっちゃ
    0.76
     downright
    0.75
     conformément
    0.75
     BECAUSE
    0.74
    POSITIVE LOGITS
     Ре
    0.90
     ;\
    0.78
     Solve
    0.77
    },\
    0.74
    Ꮢ
    0.73
     …,
    0.73
    ];
    0.73
     fakat
    0.72
     ;,
    0.70
     Можно
    0.69
    Activations Density 0.034%

    No Known Activations