© 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. 73181
    Prev
    Next
    INDEX
    Explanations

    action followed by object

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

    canvas element processing

    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
    ContactBundle
    0.55
    йин
    0.52
     వీరి
    0.51
     тях
    0.51
     набор
    0.48
    Mother
    0.48
     estan
    0.48
    ی
    0.48
     подходя
    0.47
     दो
    0.47
    POSITIVE LOGITS
    anna
    0.51
     genotype
    0.45
     Bernoulli
    0.45
    iel
    0.43
    édie
    0.43
    <0xE3>
    0.42
    0.42
    atto
    0.42
    inv
    0.42
     survey
    0.41
    Activations Density 0.000%

    No Known Activations