© 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. 75965
    Prev
    Next
    INDEX
    Explanations

    foreign language and animals

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

    explosions, environments, gas

    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
    不仅仅
    0.50
     ministerial
    0.48
    欄
    0.46
     Statements
    0.45
    诸多
    0.45
    更为
    0.44
    互联网档案馆
    0.42
    兢
    0.42
     ;,
    0.41
     Historically
    0.41
    POSITIVE LOGITS
    bbene
    0.56
     insectes
    0.53
     crippled
    0.50
    }+\
    0.48
    はある
    0.47
     paredes
    0.46
    もない
    0.46
     entfer
    0.46
    }=\
    0.45
     animaux
    0.45
    Activations Density 0.000%

    No Known Activations