© 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. 133771
    Prev
    Next
    INDEX
    Explanations

    people looking or searching

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

    hospitality, inn, php, answer

    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
    悯
    0.46
     broadening
    0.43
    strength
    0.43
     intensification
    0.43
    ↵
    0.43
    savings
    0.42
    intens
    0.42
    ;
    0.42
     diversification
    0.41
    getInfo
    0.41
    POSITIVE LOGITS
     લોકો
    0.55
    勛
    0.52
    優れた
    0.48
    網友
    0.47
     risposta
    0.47
     debemos
    0.46
     buon
    0.46
     لوگوں
    0.46
     野
    0.46
     respondió
    0.46
    Activations Density 0.001%

    No Known Activations