© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81010
    Prev
    Next
    INDEX
    Explanations

    prevent or block

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

    convolutional filters detects patterns

    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
    馇
    0.54
     composants
    0.48
    韫
    0.47
    𝗆
    0.47
    ሎጂ
    0.47
     సహ
    0.46
     타입
    0.46
     забе
    0.46
     '';
    0.46
     далее
    0.46
    POSITIVE LOGITS
     denuncia
    0.49
     denunci
    0.46
     remittances
    0.43
     thwarted
    0.43
    ReadKey
    0.43
     disseminate
    0.43
    attempts
    0.42
     sectarian
    0.42
    outputs
    0.42
    Rem
    0.41
    Activations Density 0.000%

    No Known Activations