© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49125
    Prev
    Next
    INDEX
    Explanations

    efforts that

    np_acts-logits-general · gemini-2.5-flash-lite

    pepper, JSON, large

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     졸
    0.46
    њу
    0.44
    ore
    0.43
    ሟ
    0.43
    光谱
    0.43
     analyse
    0.42
     분석
    0.42
    zną
    0.42
    vaa
    0.42
     항
    0.42
    POSITIVE LOGITS
     الذين
    0.49
    都會
    0.46
     остались
    0.46
    فضل
    0.45
    ностей
    0.45
    EVEN
    0.44
     www
    0.44
     जिनके
    0.43
    WELL
    0.43
     continuando
    0.42
    Activations Density 0.000%

    No Known Activations