© 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. 201099
    Prev
    Next
    INDEX
    Explanations

    CLIENTI resources

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

    prices vary and fluctuate

    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
     unhappiness
    0.52
    眙
    0.52
     delighted
    0.51
     unhappy
    0.51
    ioned
    0.49
     счастли
    0.48
     happier
    0.47
     satisfied
    0.47
     perfecting
    0.47
    łej
    0.47
    POSITIVE LOGITS
     CLIENTI
    0.48
    確保
    0.46
    ETC
    0.46
    ABE
    0.45
    官
    0.44
    軍
    0.44
    ୟ
    0.44
     RESOURCES
    0.44
    勵
    0.43
    Chrom
    0.43
    Activations Density 0.001%

    No Known Activations