© 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. 242378
    Prev
    Next
    INDEX
    Explanations

    is transparency

    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
     ARR
    0.56
    т
    0.50
     AO
    0.49
    umen
    0.49
     AC
    0.48
     timeline
    0.45
     Integrating
    0.44
     ion
    0.44
     SONGS
    0.44
    τσ
    0.44
    POSITIVE LOGITS
     gemüt
    0.50
    exécution
    0.48
     važ
    0.48
     között
    0.48
    탉
    0.47
    ۰
    0.46
     često
    0.46
    ペン
    0.45
     carrière
    0.45
     specialize
    0.45
    Activations Density 0.000%

    No Known Activations