© 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. 49814
    Prev
    Next
    INDEX
    Explanations

    instructions below or following

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

    code or text above

    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
    usstsein
    0.37
    ico
    0.36
     aquell
    0.36
    icata
    0.36
    wa
    0.35
     amacıyla
    0.35
     naquela
    0.35
     ਵ
    0.35
     genutzt
    0.35
     Für
    0.35
    POSITIVE LOGITS
    上述
    1.42
    下記の
    1.34
    下記
    1.33
     aşağıdaki
    1.33
    上記の
    1.33
     उपरोक्त
    1.30
    上記
    1.30
    下列
    1.29
    以下
    1.28
     berikut
    1.28
    Activations Density 0.127%

    No Known Activations