© 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. 154978
    Prev
    Next
    INDEX
    Explanations

    automatically saves

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

    time durations and age

    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
    SOFTWARE
    0.54
    BUTTON
    0.50
    FARE
    0.47
    Ꮁ
    0.47
    Projekt
    0.46
    ರೆ
    0.46
     PROJECT
    0.46
     projektu
    0.46
    ତା
    0.45
     PLUGIN
    0.45
    POSITIVE LOGITS
     responsable
    0.47
     عمر
    0.45
    全長
    0.43
     جرم
    0.43
     வில்
    0.43
    ashed
    0.42
     ر
    0.42
     به
    0.41
     সারাদেশ
    0.40
     Matt
    0.40
    Activations Density 0.001%

    No Known Activations