© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221351
    Prev
    Next
    INDEX
    Explanations

    literalmente, буквально, relevante

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^{[\
    0.39
    kovskij
    0.38
    avati
    0.38
    vered
    0.37
    β
    0.37
    dev
    0.36
    বায়
    0.36
    ß
    0.36
    irsty
    0.34
    cusson
    0.34
    POSITIVE LOGITS
     literalmente
    0.43
     располага
    0.42
     знамена
    0.42
     буквально
    0.42
     контек
    0.41
     undirected
    0.41
     изо
    0.40
     kontek
    0.40
     relevante
    0.40
     readonly
    0.39
    Activations Density 0.015%

    No Known Activations