© 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. 185294
    Prev
    Next
    INDEX
    Explanations

    plan to shop

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

    legitimate and safe options

    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
     하지만
    0.45
    HOUT
    0.44
    umim
    0.42
     き
    0.42
    Dutch
    0.41
    使
    0.41
    렬
    0.40
    ol
    0.39
    AddTo
    0.39
    İZ
    0.39
    POSITIVE LOGITS
    ન
    0.49
     lieber
    0.48
     Bucks
    0.46
     गरीबी
    0.45
     exhort
    0.45
     favorita
    0.45
     favoriser
    0.44
     Edwards
    0.44
     unjustly
    0.44
     mężczy
    0.44
    Activations Density 0.000%

    No Known Activations