© 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. 190605
    Prev
    Next
    INDEX
    Explanations

    placeholder pages for individuals

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

    finding specific values

    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
     дене
    0.54
    在她
    0.50
    徕
    0.47
    在前
    0.46
     показатели
    0.45
     ση
    0.45
     EVENTS
    0.44
    饿
    0.44
    मर्रा
    0.44
    极其
    0.44
    POSITIVE LOGITS
     pront
    0.49
     Colombie
    0.46
     Goode
    0.45
     manuel
    0.44
     solicita
    0.44
     chaud
    0.43
     Tales
    0.42
     Chat
    0.41
    もり
    0.41
     personnalisé
    0.41
    Activations Density 0.001%

    No Known Activations