© 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. 30437
    Prev
    Next
    INDEX
    Explanations

    proportionate comparisons

    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
     Channel
    0.46
     Considered
    0.46
     सामाजिक
    0.43
     Mogo
    0.43
    ร์
    0.42
    ▯
    0.41
     CGM
    0.41
     Conting
    0.41
     Exp
    0.40
     Motivation
    0.40
    POSITIVE LOGITS
    :
    0.43
     attravers
    0.42
    uc
    0.42
    okinase
    0.42
    edere
    0.41
    uidos
    0.41
    outes
    0.41
     promptly
    0.41
    atuur
    0.41
     wrists
    0.41
    Activations Density 0.029%

    No Known Activations