© 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. 195493
    Prev
    Next
    INDEX
    Explanations

    network and internet

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

    definitions and continuations

    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
     опасность
    0.51
    }}=-\
    0.49
     bottomLeft
    0.49
     নির্বাচিত
    0.48
     особое
    0.48
    editText
    0.47
     иметь
    0.47
     лицо
    0.47
     అన్ని
    0.47
     активность
    0.47
    POSITIVE LOGITS
     gru
    0.51
    .
    0.49
     filings
    0.49
    ritu
    0.46
    चिक
    0.46
     sealant
    0.45
    奭
    0.44
    復活
    0.44
    رم
    0.44
     mildew
    0.43
    Activations Density 0.000%

    No Known Activations