© 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. 177999
    Prev
    Next
    INDEX
    Explanations

    text messages

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

    control and targeting

    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
     accommod
    0.49
     segreg
    0.47
     empfe
    0.46
     benef
    0.46
    _{+}
    0.46
    钛
    0.45
     apo
    0.44
    铍
    0.44
     benefactor
    0.43
     tret
    0.42
    POSITIVE LOGITS
    il
    0.57
    yah
    0.53
    ser
    0.51
    oud
    0.49
    par
    0.49
    zaw
    0.48
    by
    0.47
    senior
    0.47
    these
    0.47
    na
    0.47
    Activations Density 0.000%

    No Known Activations