© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199047
    Prev
    Next
    INDEX
    Explanations

    writing workshop

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

    path, risk, handle

    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
    Negative Logits
    迪
    0.48
     உடனடியாக
    0.45
     छोट
    0.44
     feminism
    0.44
    𝓹
    0.44
     पड़ेगा
    0.43
     seraient
    0.43
     actuality
    0.42
    نساء
    0.42
     Marietta
    0.42
    POSITIVE LOGITS
    残留
    0.48
    aj
    0.46
    ishop
    0.46
    isfile
    0.46
    "%
    0.46
     obdob
    0.42
    ile
    0.41
    有两种
    0.41
    看不到
    0.41
    uvo
    0.40
    Activations Density 0.000%

    No Known Activations