© 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. 4764
    Prev
    Next
    INDEX
    Explanations

    quantity or state of categories

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

    states or actions

    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
    とその
    0.41
    Voilà
    0.36
    ர்
    0.35
    ."""
    0.35
    及其
    0.34
    .//
    0.32
    ener
    0.32
    \'
    0.32
     applicator
    0.31
     bood
    0.31
    POSITIVE LOGITS
     abound
    0.43
    ține
    0.40
     galore
    0.40
    が高
    0.37
    डक्शन
    0.37
     zacz
    0.35
     zostały
    0.34
     plentiful
    0.34
    從
    0.34
     soared
    0.33
    Activations Density 0.314%

    No Known Activations