© 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. 98002
    Prev
    Next
    INDEX
    Explanations

    war, flashes, swimming, anticipated

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

    Byzantine, skull, screen, sequence

    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
    رة
    0.57
    ători
    0.56
    nbhost
    0.55
    хия
    0.52
     ismi
    0.51
    ﻑ
    0.51
     tháng
    0.51
    地的
    0.50
    డ్డి
    0.49
     égaux
    0.49
    POSITIVE LOGITS
    leg
    0.48
     ):
    0.47
     keb
    0.47
     zam
    0.46
    BB
    0.46
     귀
    0.45
     극
    0.45
    Literatur
    0.45
    .,
    0.44
    mem
    0.44
    Activations Density 0.000%

    No Known Activations