© 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. 192277
    Prev
    Next
    INDEX
    Explanations

    capitalist exporting functional

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

    coherent paragraph completion

    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
    첫
    0.48
     относительно
    0.47
    엄
    0.45
    )|\
    0.45
    publicKey
    0.45
    enz
    0.44
    착
    0.43
     스타일
    0.42
    (\\
    0.42
    을
    0.42
    POSITIVE LOGITS
     nhưng
    0.53
     lekin
    0.49
     ethylene
    0.46
     Crac
    0.46
     capitalist
    0.46
    變成
    0.46
     exporting
    0.45
     functional
    0.45
     citric
    0.45
     sidew
    0.44
    Activations Density 0.000%

    No Known Activations