© 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. 247537
    Prev
    Next
    INDEX
    Explanations

    resulted in, asked for, developers alike

    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
    ç
    0.54
     dün
    0.50
    зной
    0.50
     meilleures
    0.50
     तोड़
    0.49
     ál
    0.49
    ş
    0.49
    ିକ
    0.48
     élevés
    0.47
     don
    0.47
    POSITIVE LOGITS
    風景
    0.47
    
    0.47
    תה
    0.45
    translator
    0.43
    多分
    0.43
    gte
    0.43
    ませんが
    0.42
    剪
    0.42
    UEFA
    0.42
    થે
    0.42
    Activations Density 0.000%

    No Known Activations