© 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. 31119
    Prev
    Next
    INDEX
    Explanations

    questions starting with what or if

    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
    愆
    0.55
    叢
    0.47
    IVITY
    0.47
     pathogenicity
    0.47
    贛
    0.47
     crítica
    0.45
     अभिव्य
    0.45
    飭
    0.45
    utiva
    0.44
     кризи
    0.44
    POSITIVE LOGITS
     freck
    0.60
     surnames
    0.59
     odd
    0.55
     oldest
    0.51
     potatoes
    0.51
     pineapple
    0.51
    odd
    0.50
     eyebrows
    0.50
     toothpaste
    0.50
     eyelashes
    0.50
    Activations Density 0.147%

    No Known Activations