© 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. 74805
    Prev
    Next
    INDEX
    Explanations

    Kitipat, Book, MRI, Spa, watch, Schrödinger, PE

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

    specific entities and concepts

    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
    Бар
    0.49
    До
    0.47
    ША
    0.42
    ALL
    0.42
    п
    0.42
    Ба
    0.41
    ≥
    0.41
    ≳
    0.41
    лия
    0.41
    ซ์
    0.41
    POSITIVE LOGITS
     aeronaut
    0.46
     szok
    0.45
     widows
    0.44
     awa
    0.44
     laboratorium
    0.43
     asing
    0.43
     aik
    0.42
     travailleurs
    0.42
     enfermos
    0.42
     penyakit
    0.42
    Activations Density 0.005%

    No Known Activations