© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 68583
    Prev
    Next
    INDEX
    Explanations

    solidated, trustworthiness, returned, months

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

    entity declaration, namespaces, status

    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
    N
    0.45
    effort
    0.45
    وز
    0.44
    Robert
    0.44
    وبي
    0.44
    ويس
    0.43
    Nb
    0.43
    Diane
    0.43
     الوز
    0.43
            
    0.42
    POSITIVE LOGITS
     tih
    0.50
    ꒪
    0.45
     ferritin
    0.45
     chickens
    0.44
     tablecloth
    0.44
     milling
    0.44
     Bulldog
    0.44
     posuere
    0.43
    ंगामा
    0.42
     bleaching
    0.42
    Activations Density 0.000%

    No Known Activations