© 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. 228197
    Prev
    Next
    INDEX
    Explanations

    custom orders

    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
    萌
    0.46
     кстати
    0.44
     பாத
    0.44
    شانی
    0.43
     ব্যতিক্রম
    0.42
     midfield
    0.42
    ग्विजय
    0.42
     муж
    0.41
     முயற்சி
    0.41
     korban
    0.40
    POSITIVE LOGITS
    ير
    0.49
    d
    0.48
    횽
    0.48
    Nous
    0.47
    ଦ
    0.47
    ineux
    0.46
    Hull
    0.46
    ':
    0.46
    années
    0.45
    espèces
    0.45
    Activations Density 0.000%

    No Known Activations