© 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. 22632
    Prev
    Next
    INDEX
    Explanations

    contact directly

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

    contact your

    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
    guests
    0.40
     доступа
    0.38
    nil
    0.38
    assemble
    0.38
    違反
    0.38
    decrease
    0.38
     बला
    0.38
    ਟ
    0.38
    construct
    0.38
    LinkedList
    0.37
    POSITIVE LOGITS
     scelte
    0.52
     decisions
    0.48
     tercih
    0.45
     Vivian
    0.45
     Variante
    0.45
     trimester
    0.45
     decisión
    0.44
     decisiones
    0.44
     zuerst
    0.44
     nicest
    0.44
    Activations Density 0.001%

    No Known Activations