© 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. 52459
    Prev
    Next
    INDEX
    Explanations

    api schema description summary response

    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
    ackel
    0.44
    τητας
    0.44
    টারের
    0.42
    窨
    0.39
    dining
    0.39
    ointees
    0.39
    𝗱
    0.38
     Kne
    0.38
    gaxModule
    0.37
    菓
    0.36
    POSITIVE LOGITS
     response
    0.44
     Oper
    0.44
    ApiOperation
    0.43
     notes
    0.42
     операции
    0.41
     evitare
    0.40
     Responses
    0.40
    响应
    0.39
     Seorang
    0.39
    응
    0.39
    Activations Density 0.005%

    No Known Activations