© 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. 53998
    Prev
    Next
    INDEX
    Explanations

    run into, disintegration in, or victory over

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

    offering, enthusiastically

    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
    _
    0.46
    нде
    0.44
     जानने
    0.43
    澳大利
    0.42
     umumnya
    0.41
    特徴
    0.41
     Германия
    0.41
    ᱪ
    0.41
    มอ
    0.41
    台風
    0.41
    POSITIVE LOGITS
     lept
    0.50
    Lr
    0.49
     lir
    0.48
     hydroxyl
    0.48
     św
    0.46
    이스
    0.45
    leton
    0.45
    insulin
    0.45
     Sereth
    0.44
     induce
    0.44
    Activations Density 0.000%

    No Known Activations