© 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. 50718
    Prev
    Next
    INDEX
    Explanations

    above and beyond

    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
     confession
    0.43
     рад
    0.42
     CONTRIBUTION
    0.41
     রাখিয়া
    0.40
     confess
    0.39
     SEASON
    0.39
     شد
    0.38
    醯
    0.38
     skilful
    0.38
     rhyth
    0.38
    POSITIVE LOGITS
     extra
    1.09
     ekstra
    1.02
    extra
    1.01
    Extra
    0.98
     Extra
    0.95
    EXTRA
    0.91
     EXTRA
    0.90
     extras
    0.85
    额外
    0.85
    额外的
    0.76
    Activations Density 0.033%

    No Known Activations