© 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. 153614
    Prev
    Next
    INDEX
    Explanations

    Dakota sounds, although undoubtedly

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

    steps for defining or building

    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
     ત્યારે
    0.46
    皇
    0.44
     sức
    0.40
    於
    0.39
    Tata
    0.39
    zyloxy
    0.39
    <th>
    0.38
    사는
    0.38
    raulic
    0.38
    tele
    0.37
    POSITIVE LOGITS
     měla
    0.56
     miała
    0.52
     یخ
    0.52
     uwagę
    0.51
     analiza
    0.50
     інші
    0.50
     innych
    0.49
     měl
    0.49
     trex
    0.48
     objecting
    0.48
    Activations Density 0.000%

    No Known Activations