© 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. 247476
    Prev
    Next
    INDEX
    Explanations

    IME on it

    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
     Juliette
    0.45
     Factor
    0.45
     Hampton
    0.44
    孃
    0.43
     Kensington
    0.43
     planners
    0.41
    銜
    0.41
     promotion
    0.41
     position
    0.41
     Getty
    0.41
    POSITIVE LOGITS
    Alumno
    0.55
    ไว
    0.53
     ስ
    0.51
    MathMarks
    0.51
     effectually
    0.50
    หล
    0.48
    ificante
    0.48
    Cpu
    0.47
    Incrementor
    0.47
    Alien
    0.47
    Activations Density 0.000%

    No Known Activations