© 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. 160456
    Prev
    Next
    INDEX
    Explanations

    Muslim Brotherhood, resource discovery, ILO

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

    metaphor and examples

    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
     aaye
    0.52
    濯
    0.52
    าย
    0.51
     ajud
    0.51
     ruangan
    0.51
    पणे
    0.50
     मददगार
    0.49
     expresa
    0.49
     soov
    0.48
     pregunt
    0.48
    POSITIVE LOGITS
    安
    0.48
    xf
    0.46
    pd
    0.46
    nextDouble
    0.45
    books
    0.45
     সর্বত্র
    0.45
    lof
    0.45
    MS
    0.45
    xv
    0.44
    C
    0.44
    Activations Density 0.000%

    No Known Activations