© 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. 57784
    Prev
    Next
    INDEX
    Explanations

    gather together

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

    HTML form input and attributes

    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
    ⌵
    0.49
    ريقة
    0.48
     Гинд
    0.48
    refrac
    0.48
    ﺍ
    0.47
    iectasis
    0.46
     заболевания
    0.44
    𝒽
    0.44
    ﺁ
    0.44
    endorong
    0.42
    POSITIVE LOGITS
     combine
    0.45
     nothing
    0.45
     on
    0.43
     at
    0.42
     NOTHING
    0.41
     to
    0.40
     mix
    0.40
     preamble
    0.40
     E
    0.39
     state
    0.39
    Activations Density 0.000%

    No Known Activations