© 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. 37575
    Prev
    Next
    INDEX
    Explanations

    academic publications and citations

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

    content generation and analysis

    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
    idious
    0.58
    Occupation
    0.52
    it
    0.51
     intimately
    0.51
    ,​
    0.50
    Particip
    0.50
    an
    0.49
    Shadow
    0.48
     quintessential
    0.47
    Trusted
    0.47
    POSITIVE LOGITS
     তল
    0.51
     ৬০
    0.49
    㴓
    0.47
     kerk
    0.47
     校
    0.46
     Assessments
    0.46
     measurement
    0.46
    椅子
    0.45
     Measurement
    0.45
     പരിശോധ
    0.44
    Activations Density 0.000%

    No Known Activations