© 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. 29385
    Prev
    Next
    INDEX
    Explanations

    math concepts and topics

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

    harmful and sexually explicit content policies

    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
     matchups
    0.49
     game
    0.44
     meets
    0.44
     матч
    0.43
     ______
    0.42
     eile
    0.42
     traverses
    0.42
     equations
    0.42
     ير
    0.42
     _____
    0.42
    POSITIVE LOGITS
    regierung
    0.49
    aną
    0.42
     गुंतवण
    0.42
    কারি
    0.42
     wła
    0.41
     कोणत्याही
    0.41
     ਆਪਣੇ
    0.41
    ποίηση
    0.41
     പൂര്‍
    0.40
     इसी
    0.40
    Activations Density 0.000%

    No Known Activations