© 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. 161914
    Prev
    Next
    INDEX
    Explanations

    proposal to pursue owning course

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

    Process Relevance, when you

    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
     compilation
    0.45
     fermented
    0.42
    از
    0.41
     clear
    0.40
     soft
    0.39
     self
    0.39
    USER
    0.39
     ډ
    0.39
     Đại
    0.39
     pulsating
    0.38
    POSITIVE LOGITS
    存档备份
    0.54
     números
    0.53
     éxito
    0.53
    리의
    0.52
    톄
    0.52
     factores
    0.52
    ความ
    0.52
     núcle
    0.51
     módulos
    0.51
    ㈢
    0.51
    Activations Density 0.000%

    No Known Activations