© 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. 107054
    Prev
    Next
    INDEX
    Explanations

    hypnosis, theology, male, protector

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

    avoid screens, method, string.join, generators

    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
     provo
    0.50
    IllegalArgument
    0.50
    Frame
    0.48
     auster
    0.48
    م
    0.47
     provoca
    0.46
    Chorus
    0.46
     サ
    0.46
    orElse
    0.46
     tasarım
    0.46
    POSITIVE LOGITS
     Peacock
    0.47
     kep
    0.46
    นำ
    0.45
    ﻭ
    0.43
    但是
    0.43
     Kep
    0.43
    อก
    0.42
     Encounter
    0.42
    蔦
    0.41
    தான
    0.41
    Activations Density 0.000%

    No Known Activations