© 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. 114845
    Prev
    Next
    INDEX
    Explanations

    immaculate purity

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

    crucial/steeped/access followed by preposition

    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
    ﻼ
    0.57
    jsr
    0.52
    ala
    0.51
    ్రియ
    0.51
    esters
    0.50
    bi
    0.50
    h
    0.50
    os
    0.49
    ariya
    0.49
    hous
    0.48
    POSITIVE LOGITS
     економі
    0.49
     menikah
    0.49
     Sharks
    0.48
     temporadas
    0.48
     immaculate
    0.47
     másc
    0.47
     paired
    0.47
     Iván
    0.47
     식으로
    0.46
     NITRO
    0.46
    Activations Density 0.000%

    No Known Activations