© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99602
    Prev
    Next
    INDEX
    Explanations

    should have, know you, found by, same as

    np_acts-logits-general · gemini-2.5-flash-lite

    opens a door

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    িসি
    0.46
     Cala
    0.46
    ิ้ง
    0.44
    素晴
    0.43
     fixer
    0.43
     fixing
    0.42
     Curl
    0.42
    逑
    0.42
    要素
    0.41
    ”（
    0.41
    POSITIVE LOGITS
    tır
    0.52
    instit
    0.49
    tych
    0.47
     Unterstüt
    0.46
     wym
    0.45
     النسب
    0.45
     التمثيل
    0.44
    rams
    0.43
     djel
    0.43
    śmy
    0.42
    Activations Density 0.000%

    No Known Activations