© 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. 109400
    Prev
    Next
    INDEX
    Explanations

    doing what

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

    earning and roleplay

    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
    inscription
    0.47
     ક્
    0.47
    𝑀
    0.47
    ω
    0.46
     составе
    0.46
     थंड
    0.46
    𝑠
    0.46
     सागरी
    0.46
    ሖ
    0.45
     році
    0.45
    POSITIVE LOGITS
     Globally
    0.48
     err
    0.46
     Generate
    0.46
     Navigate
    0.46
     Generated
    0.44
     harm
    0.44
     migrate
    0.43
     achieve
    0.43
     parse
    0.43
     unsafe
    0.43
    Activations Density 0.000%

    No Known Activations