© 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. 197561
    Prev
    Next
    INDEX
    Explanations

    verb or noun followed by preposition or noun

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

    emotional release, convey termination, write, addresses

    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
    寶
    0.47
    合った
    0.46
    SendData
    0.43
     fused
    0.42
    ूँगा
    0.42
     Listo
    0.42
     Leer
    0.41
    簡易
    0.40
     loosened
    0.40
    補充
    0.40
    POSITIVE LOGITS
     دیک
    0.52
     어떻게
    0.48
     괴
    0.46
    mith
    0.46
     dotyczące
    0.44
     manifestly
    0.44
     anto
    0.44
     谢
    0.44
     iso
    0.43
    tert
    0.43
    Activations Density 0.002%

    No Known Activations