© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    whispered secrets or tales

    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
    бы
    0.47
    มี
    0.47
     Team
    0.44
     FW
    0.43
    명
    0.43
    inske
    0.43
    q
    0.42
    리
    0.42
    程式
    0.41
    ท์
    0.41
    POSITIVE LOGITS
     perfettamente
    0.49
     femenina
    0.46
     რომელი
    0.45
     chopsticks
    0.45
    phthalm
    0.44
     aspirin
    0.44
     acupuncture
    0.44
     ovens
    0.43
    pyrrol
    0.43
    vacancy
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.