© 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. 147577
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions of entities

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

    explains refusal of explicit content

    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
     उपयोगी
    0.51
    item
    0.50
    circ
    0.48
     benutzt
    0.45
    ]];
    0.44
     निकाला
    0.43
    ired
    0.43
    amba
    0.42
    }\}
    0.42
    stantial
    0.42
    POSITIVE LOGITS
     Filling
    0.50
     Harlow
    0.49
     Michelle
    0.48
    Filling
    0.48
     Eileen
    0.47
     Roosevelt
    0.47
     Anita
    0.47
     Voters
    0.47
     Stephen
    0.45
    ൭
    0.45
    Activations Density 0.001%

    No Known Activations