© 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. 163681
    Prev
    Next
    INDEX
    Explanations

    separated by listing

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

    potentially leading to outcomes

    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
     COLORS
    0.44
    市民
    0.43
    ilt
    0.40
    工程
    0.40
     remarquable
    0.40
     ši
    0.40
     zuverläss
    0.39
    品
    0.39
    ५
    0.39
     材料
    0.39
    POSITIVE LOGITS
    KHTML
    0.49
     detonation
    0.47
    alada
    0.47
     Enfield
    0.46
     explosive
    0.46
     Paradis
    0.45
    पाउंड
    0.44
     Lightfoot
    0.43
    щем
    0.42
    WithOptions
    0.42
    Activations Density 0.001%

    No Known Activations