© 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-262K
    7. 204538
    Prev
    Next
    INDEX
    Explanations

    token and tokens

    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_262k_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
     stain
    0.45
     staining
    0.42
     teaching
    0.41
     donor
    0.40
     জি
    0.40
    텨
    0.40
     gom
    0.39
     stained
    0.39
     ectopic
    0.39
    煅
    0.39
    POSITIVE LOGITS
     Token
    1.02
    Token
    0.99
    令牌
    0.93
     token
    0.90
     tokens
    0.90
     Tokens
    0.90
     TOKEN
    0.89
    Tokens
    0.88
    TOKEN
    0.84
     टोक
    0.84
    Activations Density 0.111%

    No Known Activations