© 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. 40164
    Prev
    Next
    INDEX
    Explanations

    semi-structured interviews

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

    important AI disclaimers

    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
     disperse
    0.43
     diventa
    0.43
     Decl
    0.42
    uminous
    0.41
    數
    0.41
    WC
    0.41
     consid
    0.41
     deceler
    0.41
     brighten
    0.40
    䢌
    0.40
    POSITIVE LOGITS
    ügel
    0.48
     상당
    0.47
    🎙
    0.47
    ེ
    0.46
     разговор
    0.46
    iktok
    0.45
     აღმასრულებელი
    0.45
     kişiler
    0.45
    ployed
    0.44
    带领
    0.44
    Activations Density 0.000%

    No Known Activations