© 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. 19728
    Prev
    Next
    INDEX
    Explanations

    name, value, its, asset, rate

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

    economic activity, reaction, amount of XBT

    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
    t
    0.37
    it
    0.35
     தானே
    0.35
    i
    0.33
    the
    0.33
    hua
    0.32
    argon
    0.32
    ��
    0.32
    emaster
    0.32
    uga
    0.32
    POSITIVE LOGITS
     estés
    0.36
     deven
    0.35
     komplex
    0.34
     besonders
    0.33
     entsprechend
    0.33
     ८
    0.33
    ؤں
    0.33
    𝟖
    0.33
    linkOpacity
    0.32
    ٧
    0.32
    Activations Density 0.000%

    No Known Activations