© 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. 189960
    Prev
    Next
    INDEX
    Explanations

    website content and resources

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

    records element, fix:, recognizing statement

    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
    SYSTEM
    0.47
    Unit
    0.46
    Chrome
    0.46
    xiii
    0.46
    ว้
    0.45
    chrome
    0.45
    firefox
    0.44
    "-"
    0.44
    Bitmap
    0.44
    ."-
    0.43
    POSITIVE LOGITS
     casas
    0.58
     worsened
    0.54
     grasped
    0.51
     Casas
    0.48
     lodges
    0.47
     sheltered
    0.46
     aggravated
    0.46
     warped
    0.46
     vultures
    0.46
     comprehend
    0.45
    Activations Density 0.000%

    No Known Activations