© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205492
    Prev
    Next
    INDEX
    Explanations

    lmao, knots, cafes, $

    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
     pharmaceutical
    0.40
     LEAD
    0.39
     NEL
    0.39
    uniqueItems
    0.38
    WEI
    0.38
     estrellas
    0.38
     superstitious
    0.38
    ﺄ
    0.38
    NETT
    0.38
     MARRI
    0.38
    POSITIVE LOGITS
     nights
    0.37
     Nights
    0.37
     inget
    0.36
     WP
    0.36
     séquence
    0.36
    ből
    0.36
     सीक्वेंस
    0.35
     components
    0.35
     aquí
    0.34
    tribe
    0.34
    Activations Density 0.001%

    No Known Activations