© 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. 34450
    Prev
    Next
    INDEX
    Explanations

    German Beer Purity Law

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

    trademark availability

    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
    paysys
    0.45
    INFRINGEMENT
    0.42
     reluctantly
    0.41
    StarObject
    0.41
    ന്വേഷ
    0.41
    楦
    0.41
     საბ
    0.41
     loser
    0.41
    DataXYZ
    0.40
    LOTREntity
    0.40
    POSITIVE LOGITS
     første
    0.53
    CM
    0.50
    '
    0.48
    CS
    0.47
    чні
    0.46
    )
    0.45
    CT
    0.45
    لق
    0.45
     crystalline
    0.44
    чний
    0.43
    Activations Density 0.000%

    No Known Activations