© 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. 200629
    Prev
    Next
    INDEX
    Explanations

    your item or player

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

    creating, starting, generating, introducing

    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
     exager
    0.51
     exaggerate
    0.51
    AndUpdate
    0.50
    语
    0.47
    闻
    0.47
     lé
    0.46
    会
    0.45
    út
    0.43
     exagger
    0.43
    线
    0.43
    POSITIVE LOGITS
     surviv
    0.52
     Shutterstock
    0.47
    gling
    0.46
     वैल्यू
    0.43
    heiten
    0.43
    efficients
    0.43
     Surviv
    0.42
     hydrochloride
    0.42
    pxy
    0.42
     Hydrochloride
    0.41
    Activations Density 0.000%

    No Known Activations