© 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. 51583
    Prev
    Next
    INDEX
    Explanations

    silly excuses, crucial, button

    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
    :
    0.55
    通過
    0.45
     terminology
    0.44
    類型
    0.44
    罰
    0.43
    卒業
    0.43
    術
    0.43
    頸
    0.43
     marina
    0.42
     scoring
    0.42
    POSITIVE LOGITS
     êtres
    0.47
    企业
    0.46
    掌控
    0.46
     véritables
    0.46
    Մ
    0.46
    企业的
    0.45
     bravely
    0.45
    ྛ
    0.45
     humbly
    0.45
     gemüt
    0.45
    Activations Density 0.009%

    No Known Activations