© 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. 184675
    Prev
    Next
    INDEX
    Explanations

    email domain names

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

    specific phenomena

    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
     PROFILE
    0.45
    related
    0.45
    pa
    0.44
    Դ
    0.42
    PA
    0.42
     кі
    0.42
    els
    0.42
    maximum
    0.41
    ική
    0.41
     కి
    0.40
    POSITIVE LOGITS
     altres
    0.52
     antérieure
    0.46
    ジット
    0.45
    သောအ
    0.45
     percobaan
    0.44
     exemples
    0.42
    敎
    0.42
     nymphs
    0.42
    чь
    0.41
     cardiomyocytes
    0.40
    Activations Density 0.000%

    No Known Activations