© 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. 170210
    Prev
    Next
    INDEX
    Explanations

    Sunday school, tourist attractions, upfront information

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

    often or ideally

    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
    hum
    0.46
    your
    0.45
    ung
    0.45
    alty
    0.44
    hn
    0.44
    eské
    0.44
     दोषियों
    0.44
    é
    0.44
    hid
    0.43
    Vish
    0.43
    POSITIVE LOGITS
     있을
    0.52
     utilise
    0.50
     utilising
    0.49
    ByMerging
    0.49
     utilises
    0.49
     часто
    0.48
     πραγ
    0.46
     ideally
    0.46
     Пе
    0.45
     предполагает
    0.45
    Activations Density 0.002%

    No Known Activations