© 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. 109070
    Prev
    Next
    INDEX
    Explanations

    cycles, riders, evaluation

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

    then discuss, improvement is

    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
    if
    0.54
    ό
    0.48
    very
    0.46
     ascending
    0.44
    <strong>
    0.43
    </strong>
    0.42
    module
    0.42
    function
    0.42
    Finger
    0.42
    ්‍
    0.41
    POSITIVE LOGITS
     سکے
    0.49
    PROVIDED
    0.49
     ملے
    0.48
    রোগ
    0.48
     بچوں
    0.46
     جائیں
    0.45
     وضع
    0.44
     کھول
    0.44
     بچے
    0.44
     مریض
    0.44
    Activations Density 0.002%

    No Known Activations