© 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. 72470
    Prev
    Next
    INDEX
    Explanations

    associated texts and descriptions

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

    requested technical elements and outputs

    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
    보
    0.49
    ความ
    0.48
    부
    0.45
    חי
    0.44
    悪
    0.44
    Từ
    0.44
    Platforms
    0.44
    ফ
    0.44
    جا
    0.43
    Nissan
    0.42
    POSITIVE LOGITS
     才
    0.55
    izontal
    0.52
    اونلو
    0.50
     деятельности
    0.48
     तकरीबन
    0.48
     sank
    0.47
     Eleventh
    0.46
     あなた
    0.46
     sink
    0.46
     QtWidgets
    0.46
    Activations Density 0.000%

    No Known Activations