© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 49332
    Prev
    Next
    INDEX
    Explanations

    offers powerful

    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
    𒆷
    0.44
    >\<^
    0.42
     کئی
    0.38
    гран
    0.38
     คะ
    0.38
     karane
    0.37
    মাধ্যম
    0.37
    &+
    0.37
    㖮
    0.37
    ImageQueue
    0.36
    POSITIVE LOGITS
    actin
    0.41
    kid
    0.39
    protective
    0.39
    photos
    0.38
     hadir
    0.38
     feel
    0.38
    it
    0.38
    Ft
    0.38
     photos
    0.38
    Mich
    0.37
    Activations Density 0.000%

    No Known Activations