© 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. 5717
    Prev
    Next
    INDEX
    Explanations

    hosting plans

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

    banking debt commitment

    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
    is
    0.69
    i
    0.65
    rt
    0.65
    da
    0.64
    v
    0.64
    ri
    0.63
    nt
    0.60
    w
    0.60
    nd
    0.60
    im
    0.60
    POSITIVE LOGITS
     baseApiPath
    0.57
    PAssignment
    0.53
    ləş
    0.53
     الطلبه
    0.52
     keyValue
    0.52
     эксплуа
    0.52
     mischiev
    0.52
     euclidean
    0.51
     جمله
    0.51
     خمسه
    0.50
    Activations Density 0.000%

    No Known Activations