© 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. 150963
    Prev
    Next
    INDEX
    Explanations

    location

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

    purpose and definition

    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
    ﻤ
    0.49
    繕
    0.44
    功夫
    0.44
    cua
    0.43
    汝
    0.43
     Балтбет
    0.43
    救援
    0.42
    些
    0.42
    揺
    0.42
    BinBuf
    0.41
    POSITIVE LOGITS
    ।
    0.52
     Living
    0.51
     Trustees
    0.51
     Beats
    0.51
    !
    0.51
     Boys
    0.50
     III
    0.50
     Lieutenant
    0.49
     Head
    0.49
     Columbia
    0.49
    Activations Density 0.001%

    No Known Activations