© 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. 158344
    Prev
    Next
    INDEX
    Explanations

    first hand

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

    NFTs market and sale

    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
     reproduce
    0.46
     Morphology
    0.46
    惬
    0.45
     Hist
    0.44
     microbiota
    0.43
     Rhiz
    0.42
     Prothorax
    0.41
    лос
    0.41
     Deduction
    0.41
     Gym
    0.40
    POSITIVE LOGITS
     a
    0.49
    ai
    0.49
     october
    0.46
    January
    0.46
    achery
    0.45
    aih
    0.45
    aku
    0.44
    Soviet
    0.44
    纽约
    0.44
    anny
    0.43
    Activations Density 0.000%

    No Known Activations