© 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. 115815
    Prev
    Next
    INDEX
    Explanations

    basic knowledge, many with

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

    save changes

    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
    acionales
    0.49
    árs
    0.47
     importing
    0.44
    érg
    0.44
    placement
    0.43
    deel
    0.43
    ୀ
    0.43
    acionais
    0.42
    inales
    0.42
    tero
    0.42
    POSITIVE LOGITS
     Recognize
    0.42
    Но
    0.42
     dokon
    0.42
    これにより
    0.41
    ዋ
    0.41
    ος
    0.40
     سک
    0.39
     Но
    0.39
    هی
    0.39
     Rhys
    0.38
    Activations Density 0.000%

    No Known Activations