© 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. 12853
    Prev
    Next
    INDEX
    Explanations

    extreme size or intensity

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

    huge importance or quantity

    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
    اہم
    0.69
    꽤
    0.69
    ир
    0.66
    най
    0.64
    эх
    0.63
    ч
    0.63
    ンの
    0.62
    пер
    0.61
    έρ
    0.61
    ς
    0.61
    POSITIVE LOGITS
    无比
    0.93
    8
    0.91
     unbelievably
    0.80
    9
    0.79
     огром
    0.78
     absolutamente
    0.75
     horribly
    0.74
     ogrom
    0.72
     fucking
    0.71
     רו
    0.71
    Activations Density 0.199%

    No Known Activations