© 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. 233440
    Prev
    Next
    INDEX
    Explanations

    make your, damage however, live guests, with Windows

    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
    ধির
    0.49
    થમ
    0.49
    Evalu
    0.47
    मोहन
    0.46
     règne
    0.46
     ukaz
    0.46
    暾
    0.45
    Denominator
    0.45
     dużo
    0.45
     guvern
    0.45
    POSITIVE LOGITS
    kind
    0.55
    rl
    0.51
    s
    0.51
    ield
    0.50
    nd
    0.48
     Zealand
    0.48
    field
    0.48
    transfected
    0.47
    sil
    0.47
    zeta
    0.46
    Activations Density 0.000%

    No Known Activations