© 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. 79585
    Prev
    Next
    INDEX
    Explanations

    click or step

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

    explaining and answering questions

    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
     was
    0.52
     был
    0.50
    assan
    0.48
     همچنین
    0.48
    Still
    0.46
     belirt
    0.46
    贾
    0.45
     धन
    0.45
    Bub
    0.43
    Elater
    0.43
    POSITIVE LOGITS
     SEARCH
    0.53
     account
    0.50
     search
    0.46
     microcosm
    0.45
     regimes
    0.44
     EDA
    0.44
     Search
    0.43
     Academy
    0.43
     NPR
    0.43
     interventi
    0.42
    Activations Density 0.001%

    No Known Activations