© 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. 98354
    Prev
    Next
    INDEX
    Explanations

    Boston, with items

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

    concepts with descriptors

    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
     acorns
    0.42
     PCBs
    0.42
     rodents
    0.41
     সমুদ
    0.40
    藏
    0.39
    炽
    0.39
     patente
    0.38
     hongos
    0.38
     epitope
    0.38
     கண்டு
    0.38
    POSITIVE LOGITS
    ną
    0.49
     мог
    0.47
    انی
    0.47
     कुर्सी
    0.47
    屒
    0.45
    镤
    0.45
     threefold
    0.45
    inske
    0.44
    лік
    0.44
     પ્રિય
    0.44
    Activations Density 0.001%

    No Known Activations