© 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. 53475
    Prev
    Next
    INDEX
    Explanations

    figurative art, accept my apologies, comfort to, toe boxes

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

    states not enterprise felt actively create debt

    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
    })}{
    0.48
    య
    0.47
    不超过
    0.46
    rát
    0.45
    rov
    0.44
    最后
    0.43
    as
    0.43
    铀
    0.43
     Hadamard
    0.42
    加热
    0.42
    POSITIVE LOGITS
     nyaman
    0.54
    ρυθ
    0.54
     mengapa
    0.51
    います
    0.46
    мії
    0.46
    ﻲ
    0.46
     jangka
    0.45
     verdi
    0.45
     stagnant
    0.45
     tono
    0.45
    Activations Density 0.000%

    No Known Activations