© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    entering into places or situations

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

    dive into topics

    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
     alatt
    0.27
    ពីរ
    0.27
     Auswirkungen
    0.26
     Ärzte
    0.25
    CHECKS
    0.25
    សម្រាប់
    0.25
    annten
    0.25
     ﺍ
    0.25
     kanggo
    0.25
     Angaben
    0.24
    POSITIVE LOGITS
     deeper
    0.36
     uncharted
    0.35
     into
    0.33
     ситуации
    0.32
     realms
    0.31
    ዚህ
    0.31
     wonderland
    0.31
     cyberspace
    0.30
     the
    0.30
    สู่
    0.29
    Activations Density 0.493%

    No Known Activations