© 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. 257
    Prev
    Next
    INDEX
    Explanations

    foreign language abbreviations

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

    context-dependent instructions

    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
     ‌
    0.36
     యొక్క
    0.36
     {\
    0.35
     কিংবা
    0.34
    🚱
    0.34
    的具体
    0.33
    这种
    0.33
     soltanto
    0.33
    这样一个
    0.33
    த்தின்
    0.33
    POSITIVE LOGITS
     ellos
    0.44
     idk
    0.41
     usamos
    0.40
     $$$
    0.40
     nincs
    0.39
     ČR
    0.39
     ovviamente
    0.38
     iako
    0.38
     poma
    0.38
     होके
    0.38
    Activations Density 0.583%

    No Known Activations