© 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. 21662
    Prev
    Next
    INDEX
    Explanations

    analysis of and risk factors

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

    sense and meaning

    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
     dinast
    0.44
     अधिक
    0.43
     ب
    0.43
     bazı
    0.42
     AER
    0.42
     یا
    0.42
     یک
    0.41
     axb
    0.41
     ար
    0.41
     Aeronaut
    0.41
    POSITIVE LOGITS
     receives
    0.56
     therapeutics
    0.48
    સાય
    0.45
     reacted
    0.44
     receive
    0.43
    ў
    0.43
     protects
    0.43
     refrigeration
    0.43
     refrigerant
    0.43
    receive
    0.43
    Activations Density 0.000%

    No Known Activations