© 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. 227569
    Prev
    Next
    INDEX
    Explanations

    advent

    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
    s
    0.59
     Party
    0.54
     Genocide
    0.54
     mia
    0.54
     Lista
    0.54
     Mia
    0.53
    Mia
    0.52
    Ass
    0.50
     Ass
    0.50
     Clans
    0.50
    POSITIVE LOGITS
    ⣶
    0.48
     nought
    0.46
    vanishing
    0.46
     выпу
    0.46
     ۔
    0.45
     gdy
    0.45
     відповід
    0.45
     दैट
    0.45
    fetchone
    0.44
    வனாக
    0.44
    Activations Density 0.000%

    No Known Activations