© 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. 40369
    Prev
    Next
    INDEX
    Explanations

    preferences and specific entities

    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
    decoded
    0.45
    解码
    0.45
     occured
    0.44
    ก่
    0.44
     realizzazione
    0.44
    roscopy
    0.43
     torn
    0.43
     猫
    0.42
     borr
    0.42
    ORIG
    0.42
    POSITIVE LOGITS
    豊かな
    0.46
     adventurous
    0.43
     tumultuous
    0.43
     Swezey
    0.42
    सन
    0.41
    Bog
    0.41
     annual
    0.41
     Greenwich
    0.41
    नाने
    0.41
     خاطر
    0.40
    Activations Density 0.011%

    No Known Activations