© 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. 53526
    Prev
    Next
    INDEX
    Explanations

    back loops only

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

    greetings and instructions

    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
     though
    0.57
     I
    0.57
     reality
    0.56
     for
    0.54
    ’
    0.52
    -
    0.50
     Courage
    0.50
    7
    0.50
     through
    0.49
    3
    0.49
    POSITIVE LOGITS
     sluč
    0.59
    Eppo
    0.54
     પારિજા
    0.54
    篒
    0.54
    🜨
    0.53
    сик
    0.52
    तेक
    0.51
     삽
    0.50
    ีด
    0.50
    샹
    0.50
    Activations Density 0.000%

    No Known Activations