© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20765
    Prev
    Next
    INDEX
    Explanations

    interact, choices, sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RELATIVA
    0.44
     cabinetry
    0.42
     {}",
    0.41
     buildFor
    0.41
    个
    0.40
    ژه
    0.39
     چنین
    0.39
    又は
    0.39
    祯
    0.39
    ﻩ
    0.38
    POSITIVE LOGITS
     schnell
    0.43
    istern
    0.42
    ivid
    0.41
    on
    0.40
     erhö
    0.40
    čili
    0.40
     audiovis
    0.40
     इंस्टीट्यूट
    0.40
     rück
    0.40
    il
    0.40
    Activations Density 0.001%

    No Known Activations