© 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. 77102
    Prev
    Next
    INDEX
    Explanations

    decoded, provides, delivers

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

    potential implications for planning

    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
    hnten
    0.47
    auten
    0.46
    จริง
    0.44
    ние
    0.44
    urek
    0.43
    ası
    0.42
    keme
    0.42
    娇
    0.42
    ować
    0.42
    acağız
    0.42
    POSITIVE LOGITS
     Decoding
    0.52
     provides
    0.51
     Diseases
    0.51
     Decode
    0.49
     delivers
    0.49
     DOES
    0.49
     stratég
    0.48
     Fuels
    0.48
     trit
    0.48
     gives
    0.47
    Activations Density 0.001%

    No Known Activations