© 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. 231783
    Prev
    Next
    INDEX
    Explanations

    how to wire

    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
    /
    0.47
    Also
    0.46
    》。
    0.45
    》，
    0.43
    ください
    0.43
    estation
    0.42
    ：
    0.41
    ETER
    0.41
    est
    0.40
    ))+
    0.39
    POSITIVE LOGITS
     Evaluación
    0.55
     opérés
    0.52
     Hur
    0.52
     Gomes
    0.52
     городской
    0.51
     aguas
    0.51
     赵
    0.50
     Quito
    0.50
     Eshelby
    0.50
     âmbito
    0.49
    Activations Density 0.001%

    No Known Activations