© 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. 60744
    Prev
    Next
    INDEX
    Explanations

    sufficient. , yellow, February, on, hands

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

    often limited gap

    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
    0.57
     i
    0.53
     (
    0.52
    x
    0.52
     le
    0.52
     x
    0.51
    >
    0.51
     j
    0.50
     first
    0.50
    r
    0.50
    POSITIVE LOGITS
    完成后
    0.53
     necessária
    0.53
     przedsiębior
    0.51
     publicación
    0.50
    ujemo
    0.50
     সনদ
    0.50
     determinación
    0.50
     sebagaimana
    0.49
     публі
    0.49
    ваме
    0.49
    Activations Density 0.000%

    No Known Activations