© 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. 194939
    Prev
    Next
    INDEX
    Explanations

    me more labour

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

    unary operators, lungs, wolves

    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
    Artists
    0.46
     Introduced
    0.44
    kräfte
    0.44
    Clients
    0.44
     providers
    0.42
    糕
    0.42
    artists
    0.42
     artistes
    0.42
     Jugendliche
    0.42
     Manuscripts
    0.42
    POSITIVE LOGITS
    adece
    0.41
     vadati
    0.41
     деше
    0.41
     Mellon
    0.41
    仯
    0.41
    ння
    0.40
    的名字
    0.40
    דול
    0.39
     miser
    0.38
    )$$
    0.38
    Activations Density 0.000%

    No Known Activations