© 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. 184318
    Prev
    Next
    INDEX
    Explanations

    designate, allow, professional

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

    Flux offers certain data features

    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
     DataTypes
    0.49
     Objet
    0.45
    对象的
    0.44
     Objects
    0.44
     arXiv
    0.43
     poked
    0.43
     都
    0.42
    Datas
    0.41
     Untersuchungen
    0.41
    骥
    0.41
    POSITIVE LOGITS
     conceivably
    0.45
    approximation
    0.43
     ceased
    0.42
     designating
    0.42
    াইভ
    0.42
    designated
    0.41
     diverting
    0.41
    therefore
    0.41
     designate
    0.41
     округу
    0.41
    Activations Density 0.001%

    No Known Activations