© 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. 46502
    Prev
    Next
    INDEX
    Explanations

    conditional actions

    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
     มัน
    0.49
     כמה
    0.46
    d
    0.46
    Sometimes
    0.44
     भारत
    0.43
    Were
    0.42
    t
    0.41
    ió
    0.41
    aises
    0.40
    Fernseh
    0.40
    POSITIVE LOGITS
    ⌵
    0.48
     access
    0.48
     appointments
    0.46
     lift
    0.45
     expedite
    0.45
     pula
    0.45
     worried
    0.45
     that
    0.45
     tions
    0.44
     atas
    0.44
    Activations Density 0.005%

    No Known Activations