© 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. 131054
    Prev
    Next
    INDEX
    Explanations

    restriction / prohibition

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

    introducing specific information

    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
    erdem
    0.43
     tapping
    0.43
     geometry
    0.41
     alternative
    0.41
    شاف
    0.40
    тельное
    0.40
     fall
    0.39
    謝
    0.39
    ancing
    0.38
    วันนี้
    0.38
    POSITIVE LOGITS
     restricts
    0.52
     ograni
    0.47
     ограничи
    0.46
     limitar
    0.46
    bidden
    0.46
    kona
    0.45
     தடுக்க
    0.45
    buje
    0.44
    ulitan
    0.44
    idz
    0.43
    Activations Density 0.001%

    No Known Activations