© 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. 113516
    Prev
    Next
    INDEX
    Explanations

    multi-language inputs

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

    Cumulative distribution, platforms, horror

    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
    reb
    0.44
    纶
    0.42
    nd
    0.42
     transm
    0.42
    ј
    0.41
     repre
    0.41
     بدأ
    0.41
     أح
    0.40
     أع
    0.40
     recounted
    0.39
    POSITIVE LOGITS
    小さな
    0.52
     liczb
    0.51
    Rustic
    0.51
    ಸೂ
    0.50
     piattaforma
    0.50
    ೃದ್ಧ
    0.50
    ၃
    0.49
    वू
    0.48
     spokoj
    0.48
    SALT
    0.48
    Activations Density 0.000%

    No Known Activations