© 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. 89114
    Prev
    Next
    INDEX
    Explanations

    both ... and

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

    both and

    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
     ONLY
    0.49
     three
    0.48
     drei
    0.48
     only
    0.47
    atever
    0.47
     altogether
    0.47
     аж
    0.46
    ؟
    0.46
    eight
    0.46
    only
    0.45
    POSITIVE LOGITS
     किंतु
    0.52
     그렇
    0.50
     而且
    0.47
    verständlich
    0.47
     중요한
    0.45
     naughty
    0.45
     परन्तु
    0.41
     samtidigt
    0.41
     普通
    0.40
     同时
    0.40
    Activations Density 0.098%

    No Known Activations