© 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. 35679
    Prev
    Next
    INDEX
    Explanations

    daily, local, energy, retirement

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

    lists of items or rulesnumbers or card namesspecific terms and their explanationsbiological processes (fertilization, urine)forbidden or required words

    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
    ੀ
    0.58
     poursuivre
    0.50
    discussed
    0.47
    characterized
    0.47
    特別な
    0.46
    unctional
    0.46
    as
    0.46
    deletion
    0.45
    odeling
    0.45
     वैलेंटाइन
    0.45
    POSITIVE LOGITS
    |+\
    0.48
    াদা
    0.43
    +\
    0.42
    +(\
    0.42
    及时
    0.41
     auctor
    0.40
    铎
    0.40
     Runnable
    0.40
     [+
    0.39
     заро
    0.39
    Activations Density 0.000%

    No Known Activations