© 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. 229557
    Prev
    Next
    INDEX
    Explanations

    blog post

    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
    }+$
    0.47
    V
    0.45
     desec
    0.45
    Ｍ
    0.45
     Huan
    0.44
    規範
    0.44
    Кон
    0.44
    Reg
    0.44
    舞
    0.43
    Mi
    0.42
    POSITIVE LOGITS
    ujourd
    0.51
    ivas
    0.49
     Sandals
    0.49
     ওয়
    0.49
     असलेले
    0.48
    번째
    0.48
    icana
    0.48
    idazole
    0.48
     دارای
    0.47
     aar
    0.46
    Activations Density 0.002%

    No Known Activations