© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39939
    Prev
    Next
    INDEX
    Explanations

    fixed, organization, itself, Cake, Young

    np_acts-logits-general · gemini-2.5-flash-lite

    Self-Confidence, Origin-Nationality, reboot, Hold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     වි
    0.50
     လုပ်
    0.49
     ഓ
    0.49
    ApiResponse
    0.47
     퇴
    0.46
     休
    0.46
     Δε
    0.45
     白色
    0.45
    ᱾
    0.45
     دریا
    0.44
    POSITIVE LOGITS
    i
    0.57
    י
    0.49
    ले
    0.49
    OF
    0.47
     Story
    0.42
    ي
    0.42
    set
    0.42
     Parenting
    0.42
    Weight
    0.42
    bred
    0.41
    Activations Density 0.000%

    No Known Activations