© 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. 43647
    Prev
    Next
    INDEX
    Explanations

    loss or damage

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

    defining parameters for language

    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
    یی
    0.43
     quảng
    0.41
    வத
    0.41
    ycznych
    0.41
    ibilität
    0.41
    ми
    0.40
    ິນ
    0.40
    {,}
    0.40
     chất
    0.40
     fiable
    0.40
    POSITIVE LOGITS
    $\--
    0.61
     motivo
    0.49
    ة
    0.49
    redient
    0.49
     defini
    0.49
     ความ
    0.48
    getString
    0.48
     Defining
    0.46
     অপরা
    0.46
    শিংটন
    0.46
    Activations Density 0.000%

    No Known Activations