© 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. 3885
    Prev
    Next
    INDEX
    Explanations

    let's say

    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
    いても
    0.42
    bullet
    0.41
    emper
    0.40
     pouvez
    0.37
    usalem
    0.37
    shoulder
    0.37
    啕
    0.37
    亟
    0.36
    unding
    0.36
    ucional
    0.36
    POSITIVE LOGITS
     say
    1.41
    say
    1.07
    说
    0.99
     Say
    0.98
     SAY
    0.92
    Say
    0.91
     säga
    0.90
    說
    0.85
    说是
    0.80
     sagen
    0.78
    Activations Density 0.028%

    No Known Activations