© 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. 149435
    Prev
    Next
    INDEX
    Explanations

    accepted at, all spoke, Thomas Yet

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

    data processing and specifications

    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
    ко
    0.49
     larceny
    0.45
     அரசிய
    0.44
    álie
    0.44
    <0x80>
    0.43
    ки
    0.42
    年轻
    0.42
    这么
    0.42
     medica
    0.42
    ка
    0.41
    POSITIVE LOGITS
    锜
    0.49
    FIX
    0.49
    Rotate
    0.48
    RNA
    0.48
    Butyl
    0.48
     Studien
    0.48
    UISE
    0.46
    OnOff
    0.46
     postfix
    0.46
    Mole
    0.45
    Activations Density 0.000%

    No Known Activations