© 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. 105096
    Prev
    Next
    INDEX
    Explanations

    toast & roast

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

    use instructions or commands

    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
     ambitions
    0.52
    ('/:
    0.47
     Irland
    0.44
     habitants
    0.44
     irritability
    0.43
     environs
    0.43
     longe
    0.43
    フィール
    0.43
     goals
    0.42
     bounds
    0.42
    POSITIVE LOGITS
    િક
    0.61
    osia
    0.54
    ala
    0.53
     với
    0.53
    ụng
    0.53
    ü
    0.53
     внесен
    0.51
     પર
    0.50
     bằng
    0.49
     સંખ્યા
    0.49
    Activations Density 0.000%

    No Known Activations