© 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. 227213
    Prev
    Next
    INDEX
    Explanations

    private descriptions

    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
    ר
    0.58
    략
    0.49
    북도
    0.47
    Disco
    0.47
     romances
    0.47
    λω
    0.46
    รก
    0.46
    т
    0.45
    ７
    0.45
     отсутствии
    0.45
    POSITIVE LOGITS
     گیری
    0.57
     zásobníku
    0.51
    spf
    0.50
     denkt
    0.50
    subdirectory
    0.49
    stainless
    0.48
    hdf
    0.47
     Cio
    0.47
    param
    0.47
     düşün
    0.46
    Activations Density 0.000%

    No Known Activations