© 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. 133672
    Prev
    Next
    INDEX
    Explanations

    meals and categories

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

    plants cease photosynthesis, photon and electron

    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
     località
    0.46
    Linkedin
    0.45
     Besch
    0.45
     Computational
    0.44
    িক্স
    0.44
    kHz
    0.44
     FIX
    0.43
    େ
    0.43
    vect
    0.43
    
    0.42
    POSITIVE LOGITS
    꾼
    0.51
    也不是
    0.45
     pogled
    0.45
    odos
    0.45
     shenanigans
    0.43
    őr
    0.43
     भूमिका
    0.43
     switcher
    0.42
     susceptible
    0.42
    ends
    0.41
    Activations Density 0.000%

    No Known Activations