© 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. 233311
    Prev
    Next
    INDEX
    Explanations

    printing paper

    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
    itoral
    0.46
    ঠ
    0.46
    ク
    0.45
     ovvero
    0.44
    υ
    0.44
     intravascular
    0.43
     του
    0.43
    และ
    0.43
    вари
    0.43
    хоро
    0.43
    POSITIVE LOGITS
     كات
    0.54
    忐
    0.48
     LoginForm
    0.47
     استف
    0.45
     போலவே
    0.45
     كار
    0.45
     Bewertung
    0.45
     Adventures
    0.44
     ursprünglich
    0.44
     powied
    0.43
    Activations Density 0.001%

    No Known Activations