© 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. 40596
    Prev
    Next
    INDEX
    Explanations

    complete rework

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

    #[YourCity] placeholders

    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
    0.63
    n
    0.49
    an
    0.48
    f
    0.47
     س
    0.46
    e
    0.45
    ต
    0.45
    ان
    0.45
    ="
    0.44
    her
    0.44
    POSITIVE LOGITS
    നട
    0.52
    чках
    0.49
    ঞ্জে
    0.49
    configuring
    0.49
    ση
    0.48
    ISource
    0.48
     సమావేశ
    0.48
    брав
    0.48
     tokoh
    0.47
    廣場
    0.47
    Activations Density 0.000%

    No Known Activations