© 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. 144142
    Prev
    Next
    INDEX
    Explanations

    professional writer evaluation

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

    practical instructions and information

    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
    0
    0.55
    Required
    0.52
    Sc
    0.46
    Starred
    0.46
    Player
    0.46
    ED
    0.46
    Refresh
    0.45
    Most
    0.45
    Search
    0.44
    ა
    0.44
    POSITIVE LOGITS
     conveying
    0.51
     cibo
    0.47
    blr
    0.46
     gauging
    0.45
    ské
    0.45
    ko
    0.44
    льную
    0.43
    ipelago
    0.42
     factoring
    0.42
    po
    0.42
    Activations Density 0.000%

    No Known Activations