© 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. 86456
    Prev
    Next
    INDEX
    Explanations

    LTE, ai, orma

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

    lyrics, parody, visible, edgy

    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
    เรา
    0.44
     我们
    0.44
     spectrometer
    0.44
     parameter
    0.43
     åter
    0.42
     polygon
    0.42
     シルバー
    0.42
    復
    0.42
     COMPLEX
    0.41
     возрасте
    0.41
    POSITIVE LOGITS
    ai
    0.63
    asth
    0.50
    ayım
    0.49
    elte
    0.49
    oret
    0.47
    jä
    0.47
    hell
    0.47
    orma
    0.47
    impanan
    0.47
    ail
    0.46
    Activations Density 0.002%

    No Known Activations