© 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. 94999
    Prev
    Next
    INDEX
    Explanations

    measures (ml) or specific items

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

    Ninja Turtles

    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
     стрельца
    0.55
     রাদ
    0.50
     هنوز
    0.47
    𝗠
    0.46
     проекты
    0.45
     результаты
    0.45
    <unused2126>
    0.44
     позволит
    0.44
     أَ
    0.43
     Наде
    0.42
    POSITIVE LOGITS
     D
    0.48
     hab
    0.47
     mas
    0.47
     desper
    0.46
     epile
    0.46
     freak
    0.45
     self
    0.45
     szok
    0.44
     incapac
    0.44
    øk
    0.44
    Activations Density 0.001%

    No Known Activations