© 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. 25705
    Prev
    Next
    INDEX
    Explanations

    best pictures

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

    explains cause and effect

    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
     दिखाकर
    0.41
    领域的
    0.40
     जानता
    0.40
    рующий
    0.40
    ያው
    0.39
    娣
    0.39
    の方は
    0.39
    纏
    0.39
     ด้าน
    0.39
    招待
    0.38
    POSITIVE LOGITS
     decays
    0.48
     regrets
    0.46
     decayed
    0.45
     Fresno
    0.44
     neuesten
    0.43
     mayonnaise
    0.42
    ۹
    0.42
     calories
    0.42
     discouraged
    0.41
     decreases
    0.41
    Activations Density 0.000%

    No Known Activations