© 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. 34261
    Prev
    Next
    INDEX
    Explanations

    flush-most ofcommits to

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

    harmful activities not allowed

    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
    ujú
    0.48
    ytte
    0.48
    ومه
    0.47
    కొని
    0.46
     discussed
    0.45
    imming
    0.43
    è
    0.43
    ations
    0.42
    meer
    0.42
    mming
    0.42
    POSITIVE LOGITS
    headlines
    0.49
    Ellen
    0.45
     আপাতত
    0.45
    ডে
    0.44
     arred
    0.44
     düş
    0.44
    hangman
    0.43
    🛀
    0.43
     шка
    0.43
     клавиа
    0.43
    Activations Density 0.000%

    No Known Activations