© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 117035
    Prev
    Next
    INDEX
    Explanations

    relative walk to summit

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

    attention and AJAX

    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
    '
    0.56
    ként
    0.54
     కావ
    0.52
     Platts
    0.49
     Photos
    0.47
     it
    0.47
     Phenomenology
    0.46
    "
    0.46
     Someone
    0.45
    imized
    0.45
    POSITIVE LOGITS
    娜
    0.59
    FRA
    0.55
    ром
    0.53
    FERRED
    0.53
    STOR
    0.52
    UTRON
    0.52
    )=-\
    0.51
    Deaths
    0.50
    rouge
    0.50
    дал
    0.49
    Activations Density 0.000%

    No Known Activations