© 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. 153635
    Prev
    Next
    INDEX
    Explanations

    financial or technical descriptions

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

    celebrate, harass, towns, model

    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
    Read
    0.50
    uose
    0.49
    u
    0.49
    Data
    0.47
    S
    0.47
    {
    0.46
    Sed
    0.46
    x
    0.44
    lar
    0.44
    Actual
    0.43
    POSITIVE LOGITS
     coprodu
    0.56
     desaparecido
    0.54
     incluindo
    0.54
     propon
    0.52
     aihe
    0.52
     பிரசா
    0.51
    ব্যাপ
    0.50
     konflikt
    0.50
     fichier
    0.49
     bauen
    0.49
    Activations Density 0.000%

    No Known Activations