© 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. 7094
    Prev
    Next
    INDEX
    Explanations

    grace of

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

    programming code snippets

    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
     THEM
    0.47
    訛
    0.47
    다
    0.47
    ávat
    0.46
    把他
    0.45
    ᄃ
    0.45
    at
    0.43
     starve
    0.43
    ioid
    0.42
    짱
    0.42
    POSITIVE LOGITS
     agh
    0.51
     abre
    0.48
     unang
    0.47
     insuff
    0.44
     esta
    0.43
    Ricky
    0.43
    piele
    0.42
     altern
    0.42
    ഹൃ
    0.42
    শুক্রবার
    0.42
    Activations Density 0.000%

    No Known Activations