© 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. 218979
    Prev
    Next
    INDEX
    Explanations

    future conditions

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

    DAN persona uncensored 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
    Not in Any Lists

    No Comments

    Negative Logits
     револю
    0.45
    丫
    0.43
    .​
    0.43
     principio
    0.43
     rời
    0.42
     пу
    0.42
     Ё
    0.42
    вою
    0.41
     порт
    0.41
     захід
    0.40
    POSITIVE LOGITS
    demir
    0.52
    dan
    0.51
    gbm
    0.48
     terminals
    0.47
    ssa
    0.46
    خر
    0.46
    dalam
    0.46
    deriv
    0.46
    dm
    0.45
    ధ
    0.45
    Activations Density 0.001%

    No Known Activations