© 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. 166330
    Prev
    Next
    INDEX
    Explanations

    sheep, Sizes, SLS, Muslims

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

    LED lights

    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
    a
    0.54
     popping
    0.46
     RFP
    0.45
    Setpoint
    0.45
     mandat
    0.44
     POP
    0.44
     quotient
    0.43
     rez
    0.43
     nbsp
    0.43
    outcome
    0.42
    POSITIVE LOGITS
    ஐ
    0.50
    ترك
    0.49
    ær
    0.49
    细菌
    0.49
     संस्क
    0.48
    ጂ
    0.48
    мум
    0.47
    란드
    0.47
    烪
    0.47
    𐱅
    0.47
    Activations Density 0.000%

    No Known Activations