© 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. 131193
    Prev
    Next
    INDEX
    Explanations

    sufficiency or threshold

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

    requests for details

    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
    Combining
    0.52
    扰
    0.48
    īn
    0.46
     outwe
    0.45
    rza
    0.43
    রণে
    0.43
    ប្រើ
    0.42
    矸
    0.42
    ření
    0.41
    enzi
    0.40
    POSITIVE LOGITS
     storyboard
    0.47
     крова
    0.44
     siden
    0.43
    फ्टी
    0.43
    思路
    0.43
    ophilus
    0.42
     qued
    0.42
     вдруг
    0.41
     CVS
    0.40
    很是
    0.40
    Activations Density 0.000%

    No Known Activations