© 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. 26803
    Prev
    Next
    INDEX
    Explanations

    warning

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

    accidental or typical

    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
    Atual
    0.57
    ро
    0.56
    なっている
    0.54
    乆
    0.54
    Somos
    0.52
    हमने
    0.52
    麃
    0.52
    обра
    0.51
    Lorsque
    0.50
    REVIEW
    0.49
    POSITIVE LOGITS
     warnings
    0.44
    0.44
     warning
    0.44
     Midlands
    0.43
     Tutorial
    0.43
     và
    0.42
     जनसंख्या
    0.41
     Probation
    0.41
     database
    0.40
     নিষেধ
    0.40
    Activations Density 0.000%

    No Known Activations