© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    UTF-8 encoding

    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
    avacak
    0.42
     kttt
    0.39
    "،
    0.37
     nodeList
    0.36
    າມາດ
    0.35
    မ့်
    0.35
     cristianos
    0.35
    紥
    0.34
     hồng
    0.34
     humains
    0.34
    POSITIVE LOGITS
    using
    0.40
    special
    0.36
    subject
    0.34
    void
    0.33
    tin
    0.33
    io
    0.33
    Real
    0.32
    bio
    0.32
    titan
    0.32
    rel
    0.32
    Activations Density 0.000%

    No Known Activations