© 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. 52763
    Prev
    Next
    INDEX
    Explanations

    average, events, tailoring, sharing

    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
    })^{
    0.37
     fringes
    0.37
     rockets
    0.36
     copy
    0.36
    jq
    0.36
    rockets
    0.36
     সোভিয়ে
    0.36
    ppets
    0.35
    뽕
    0.35
     ختم
    0.35
    POSITIVE LOGITS
     –,
    0.40
    __,
    0.39
    পা
    0.38
    ־
    0.38
    âu
    0.38
    flowLayoutPanel
    0.37
    ક્ર
    0.36
    слі
    0.36
    ತಾ
    0.35
     -,
    0.35
    Activations Density 0.001%

    No Known Activations