© 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. 40-GEMMASCOPE-2-RES-65K
    7. 54708
    Prev
    Next
    INDEX
    Explanations

    SAFE followed by parenthesis

    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_40_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
    চর্
    0.46
    メーター
    0.45
     ဆ
    0.44
     \,.
    0.44
    滚
    0.44
    㮍
    0.44
    蛩
    0.43
    +'.
    0.42
    经费
    0.42
    Beverungen
    0.41
    POSITIVE LOGITS
     non
    0.42
    ir
    0.40
     soft
    0.40
     ea
    0.40
     whe
    0.39
    xpath
    0.38
     wrinkle
    0.38
    Whe
    0.38
     without
    0.37
     fac
    0.37
    Activations Density 0.005%

    No Known Activations