© 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. 74633
    Prev
    Next
    INDEX
    Explanations

    elevate importance instance those occasions

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

    ambition, desires, grapes, world

    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
    nurse
    0.50
    musical
    0.47
    antie
    0.46
    كر
    0.45
    骡
    0.44
     desactiv
    0.44
    Todd
    0.44
     فبراير
    0.44
    žič
    0.44
     Crow
    0.43
    POSITIVE LOGITS
     responsibly
    0.44
     bertanggung
    0.42
    ประเทศไทย
    0.42
     compactly
    0.42
     замі
    0.42
    ̟
    0.42
     surrounded
    0.42
    AFTER
    0.41
     pursuance
    0.41
    一身
    0.41
    Activations Density 0.001%

    No Known Activations