© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    available for download

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

    descriptor-noun relationships

    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
    v
    0.49
    コント
    0.46
    iend
    0.46
    х
    0.46
    ar
    0.45
    ем
    0.45
    ار
    0.44
     instanceof
    0.44
    ном
    0.44
    વાન
    0.43
    POSITIVE LOGITS
     Игорь
    0.54
    ◑
    0.48
     oznacza
    0.47
     पोहोच
    0.47
     tingling
    0.46
     एल्गोरि
    0.46
     கலந்து
    0.46
     हुसैन
    0.46
     fonctionnent
    0.45
     questões
    0.45
    Activations Density 0.000%

    No Known Activations