© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14159
    Prev
    Next
    INDEX
    Explanations

    following "one"

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

    the word "one"

    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_16k_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
    to
    0.80
    ra
    0.65
    ur
    0.65
    /
    0.64
    re
    0.63
    person
    0.62
    /")
    0.61
    as
    0.60
    something
    0.60
    ss
    0.58
    POSITIVE LOGITS
     vô
    0.61
    を使
    0.60
     yours
    0.59
    надца
    0.58
     ones
    0.57
     utilidad
    0.57
     ours
    0.57
     milik
    0.56
    군요
    0.56
    ﻰ
    0.56
    Activations Density 0.624%

    No Known Activations