© 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. 27031
    Prev
    Next
    INDEX
    Explanations

    will notice

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

    method descriptions

    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
     干
    0.47
     cleverly
    0.45
    ien
    0.43
     झील
    0.42
     útil
    0.41
     wisely
    0.41
     ferment
    0.40
     지난해
    0.40
     Vào
    0.40
     Pull
    0.39
    POSITIVE LOGITS
    ۹
    0.49
    ۳
    0.47
    ۴
    0.47
    Tambah
    0.46
    garakan
    0.45
    郘
    0.45
    铄
    0.45
     ۲
    0.44
    кін
    0.43
    خاب
    0.43
    Activations Density 0.000%

    No Known Activations