© 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. 243349
    Prev
    Next
    INDEX
    Explanations

    Corpus Christi

    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
     grasses
    0.47
    Ꮑ
    0.42
     ሚ
    0.42
    里
    0.41
    獸
    0.40
     সঞ্চ
    0.40
     loa
    0.39
    -
    0.39
    諮
    0.39
    骰
    0.39
    POSITIVE LOGITS
    दर
    0.50
    สวัสดี
    0.49
     Retrieved
    0.47
     ajuste
    0.46
    بی
    0.46
    க்கம்
    0.46
    য়ের
    0.46
     ujung
    0.46
     علیکم
    0.45
    .”.
    0.45
    Activations Density 0.001%

    No Known Activations