© 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. 162901
    Prev
    Next
    INDEX
    Explanations

    legal processes or enforcement arrive

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

    Prometheus built, healthy sexuality

    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
     नव्या
    0.55
    アイコン
    0.50
    አ
    0.49
     metaverse
    0.48
    ष्ट
    0.48
    ທີ່ຈະ
    0.47
     CRYST
    0.47
    自分の
    0.46
    ׄ
    0.46
     Anci
    0.46
    POSITIVE LOGITS
     perpetrated
    0.46
     extermin
    0.45
     perpetrator
    0.44
     aggrieved
    0.43
     ostensibly
    0.43
     evidentiary
    0.43
     averigu
    0.42
     persecution
    0.42
     feud
    0.41
     convoluted
    0.40
    Activations Density 0.003%

    No Known Activations