© 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. 147436
    Prev
    Next
    INDEX
    Explanations

    Cover Letter Sample

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

    Modifiers **list**

    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
    イ
    0.50
    ró
    0.48
    ivät
    0.47
    이야
    0.46
    れています
    0.46
     柄
    0.45
    יית
    0.44
     будет
    0.43
    ི
    0.43
     recib
    0.43
    POSITIVE LOGITS
     unseren
    0.49
     knew
    0.48
     attenuate
    0.47
     Unser
    0.46
     Browns
    0.45
     Tabelle
    0.44
     Brahman
    0.42
     optimize
    0.42
     cahaya
    0.42
     Braun
    0.42
    Activations Density 0.003%

    No Known Activations