© 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. 218257
    Prev
    Next
    INDEX
    Explanations

    genealogical or historical data

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

    recognition of degrees and insurance

    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
     transcriptome
    0.43
    американ
    0.42
     అనేది
    0.40
    ൈ
    0.40
     είχε
    0.39
    牆
    0.39
    语音
    0.38
    ने
    0.38
    sprecher
    0.38
     equivalent
    0.37
    POSITIVE LOGITS
     関
    0.47
     いつ
    0.43
    tica
    0.42
    gid
    0.42
    忿
    0.41
    ards
    0.41
    ItemId
    0.40
     Doch
    0.40
    ObjectUnderTest
    0.40
    iddhi
    0.40
    Activations Density 0.000%

    No Known Activations