© 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. 51237
    Prev
    Next
    INDEX
    Explanations

    My Summer Car

    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
     στά
    0.49
    張
    0.49
    的
    0.48
     όμως
    0.47
    张
    0.44
    ᆫ
    0.42
    工業
    0.42
    𝗡
    0.41
    地
    0.41
    ப
    0.40
    POSITIVE LOGITS
     delusional
    0.48
     Result
    0.47
     _)
    0.47
     )(
    0.47
    yorum
    0.46
    )(
    0.45
     typos
    0.45
     dh
    0.45
    vh
    0.44
     cvec
    0.44
    Activations Density 0.007%

    No Known Activations