© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61470
    Prev
    Next
    INDEX
    Explanations

    noticing details or subtle cues

    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_31_width_65k_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
    el
    0.53
    ar
    0.49
    ochem
    0.47
    ner
    0.46
    histor
    0.45
    Express
    0.45
    I
    0.45
    node
    0.44
    TL
    0.44
    gar
    0.44
    POSITIVE LOGITS
     injecting
    0.48
     postura
    0.47
    鮪
    0.44
     watermelon
    0.44
     Markdown
    0.44
     yüksek
    0.43
    住院
    0.43
     ekstra
    0.43
     resultCode
    0.43
     약
    0.42
    Activations Density 0.008%

    No Known Activations