© 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. 53255
    Prev
    Next
    INDEX
    Explanations

    Advertisement

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

    latency significantly

    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
    夏
    0.44
     હજાર
    0.43
     তারিখ
    0.43
     किसके
    0.42
    歷
    0.42
     लैंग्वे
    0.42
     জ্যো
    0.41
    Е
    0.40
    貯
    0.40
    NewGuid
    0.39
    POSITIVE LOGITS
     et
    0.47
     infestations
    0.47
     ofta
    0.46
     โดย
    0.46
     organismos
    0.43
    WaitingTime
    0.43
    </h6>
    0.42
     breeds
    0.42
     cocok
    0.41
     oleh
    0.41
    Activations Density 0.000%

    No Known Activations