© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    previous by thread or date

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

    by criterion

    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
     একদিন
    0.44
     an
    0.43
     future
    0.40
     Gauss
    0.39
     GF
    0.39
     superconductors
    0.39
    、
    0.39
     {@
    0.38
    {@
    0.38
    ２
    0.38
    POSITIVE LOGITS
     그러니까
    0.53
    روں
    0.46
    ней
    0.45
    зывают
    0.45
     पत्रकार
    0.44
    тят
    0.44
    verbosity
    0.44
    觴
    0.43
    eux
    0.42
     слово
    0.42
    Activations Density 0.001%

    No Known Activations