© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45916
    Prev
    Next
    INDEX
    Explanations

    as phrases

    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
     mencionó
    0.48
    🧣
    0.47
    ဢ
    0.46
     Siamo
    0.45
    ɳ
    0.43
     والدہ
    0.41
    𝗼
    0.41
    🐇
    0.41
    または
    0.41
    আমরা
    0.41
    POSITIVE LOGITS
     See
    0.42
    spapers
    0.41
     देखना
    0.41
     doubtless
    0.40
     நடவடிக்கை
    0.40
     sechs
    0.40
    ubb
    0.39
    wss
    0.39
     erst
    0.38
    ह्म
    0.38
    Activations Density 0.022%

    No Known Activations