© 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. 132405
    Prev
    Next
    INDEX
    Explanations

    foreign language or text

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

    report summaries

    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
     è
    0.55
     کمی
    0.53
     الزمن
    0.53
     metoda
    0.52
     takiego
    0.52
    ("__
    0.51
     มุม
    0.51
     ڏ
    0.50
     exemplos
    0.49
     esimerk
    0.49
    POSITIVE LOGITS
    ரு
    0.55
     tortured
    0.44
    द्रोह
    0.43
     perished
    0.43
    的事情
    0.43
     chilling
    0.42
    尔
    0.42
    木
    0.42
     returned
    0.42
     которых
    0.41
    Activations Density 0.000%

    No Known Activations