© 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. 46068
    Prev
    Next
    INDEX
    Explanations

    UK nationals

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

    multiplication and formulas

    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
     وقد
    0.47
    헴
    0.46
    ϋ
    0.42
     Kapitel
    0.41
    는데요
    0.41
     Vgl
    0.40
    なんだ
    0.40
    Ellen
    0.39
     Frau
    0.39
     Daven
    0.39
    POSITIVE LOGITS
     ambiance
    0.49
     ambience
    0.46
    ਘ
    0.46
     特別
    0.43
     atmosphere
    0.42
     solito
    0.42
     प्यार
    0.41
     force
    0.40
     கடைசி
    0.40
     പോലെ
    0.40
    Activations Density 0.000%

    No Known Activations