© 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. 242047
    Prev
    Next
    INDEX
    Explanations

    altered celebrity

    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
    %+
    0.51
     نیرو
    0.45
    구나
    0.45
     گردد
    0.44
    नास
    0.43
     precip
    0.43
    നും
    0.43
     امیر
    0.43
     قی
    0.43
    حدیث
    0.43
    POSITIVE LOGITS
    ល់
    0.52
     $
    0.48
     संशोधन
    0.45
     Musical
    0.44
    出去
    0.43
     अनुसूचित
    0.41
    叫做
    0.41
    勵
    0.41
    ﺲ
    0.40
     Obamacare
    0.40
    Activations Density 0.001%

    No Known Activations