© 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. 210562
    Prev
    Next
    INDEX
    Explanations

    synchronous reverse

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

    connected vs separate

    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
    ファイルを
    0.48
    のみ
    0.46
     гражда
    0.44
    wif
    0.44
    file
    0.44
    anath
    0.44
    })-\
    0.44
     congratulate
    0.43
     thomas
    0.43
    ################
    0.42
    POSITIVE LOGITS
     বিপরীত
    0.50
     powerhouse
    0.50
     đình
    0.48
     साँप
    0.48
    崂
    0.48
     bê
    0.46
     recouvert
    0.46
     loung
    0.45
     Absorption
    0.45
     Serpent
    0.45
    Activations Density 0.000%

    No Known Activations