© 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. 103987
    Prev
    Next
    INDEX
    Explanations

    phrases like "to take" or "want me"

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

    finding `logarithm`

    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
    MM
    0.57
    Fly
    0.53
     RATES
    0.50
    NS
    0.49
    /
    0.49
    mm
    0.48
    SD
    0.48
    리와
    0.48
    WA
    0.48
    ř
    0.47
    POSITIVE LOGITS
     textAlign
    0.42
     gesturing
    0.42
    是一个
    0.40
    станти
    0.40
     చరిత్ర
    0.39
     gestalt
    0.39
     sermons
    0.39
    ถม
    0.39
     bootstrapping
    0.39
     (!$
    0.39
    Activations Density 0.000%

    No Known Activations