© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 385
    Prev
    Next
    INDEX
    Explanations

    examples

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

    example of

    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
     ascertaining
    0.64
     tačiau
    0.59
     thiab
    0.59
     mengaku
    0.58
     assessing
    0.57
    ແລະ
    0.57
     supernatants
    0.57
     a
    0.56
     moistur
    0.56
     previsto
    0.56
    POSITIVE LOGITS
     مثال
    1.09
    例子
    1.05
    Example
    1.05
    EXAMPLE
    1.03
     Beispiele
    1.01
     example
    1.00
     examples
    0.99
    Examples
    0.97
    例
    0.93
    example
    0.93
    Activations Density 0.054%

    No Known Activations