© 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. 24684
    Prev
    Next
    INDEX
    Explanations

    rock sanctuary

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

    Laplace's Demon, grief, plague, chess

    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
    🛂
    0.46
     पार्टनर
    0.44
     そして
    0.42
     Özellikle
    0.40
     ყ
    0.40
     उर्फ
    0.39
    소가
    0.39
     フランス
    0.39
    🏒
    0.39
     jūs
    0.39
    POSITIVE LOGITS
     parameters
    0.46
     enrolment
    0.45
     oposición
    0.44
     options
    0.42
     willen
    0.41
     to
    0.40
     this
    0.40
     begin
    0.40
     attempts
    0.40
     resource
    0.40
    Activations Density 0.000%

    No Known Activations