© 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-262K
    7. 35069
    Prev
    Next
    INDEX
    Explanations

    compression of, burrowing, Previous, password, dry with

    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_262k_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
     माध्य
    0.40
    ঁয়
    0.38
    *"
    0.37
    紀
    0.37
    aku
    0.36
    cpf
    0.36
     ouv
    0.36
    irov
    0.36
    饰演
    0.36
    awn
    0.35
    POSITIVE LOGITS
     ∼
    0.44
    ∼
    0.43
    檻
    0.40
    ี
    0.39
    맴
    0.38
    ابة
    0.38
    Implicit
    0.37
    BILL
    0.37
    㭐
    0.36
     े
    0.35
    Activations Density 0.000%

    No Known Activations