© 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. 178076
    Prev
    Next
    INDEX
    Explanations

    canvas art, management teams

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

    emphasis or strong recommendation

    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
     teaching
    0.48
     maju
    0.47
     perpetuity
    0.45
     तास
    0.45
    ulum
    0.45
     opportunistic
    0.44
     apartheid
    0.44
    🈷
    0.44
     ulcer
    0.44
    siswa
    0.44
    POSITIVE LOGITS
    TIC
    0.57
    מס
    0.57
    TION
    0.56
    DAC
    0.51
    HEX
    0.50
    ক
    0.50
    CAL
    0.50
    VAC
    0.50
    ુપ
    0.49
    OIL
    0.48
    Activations Density 0.001%

    No Known Activations