© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 65033
    Prev
    Next
    INDEX
    Explanations

    associations and institutions

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

    artificial intelligence and its effects

    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
    substack
    0.52
    ﹙
    0.47
    (
    0.45
    竜
    0.44
    yrıca
    0.43
     $($
    0.43
    itosan
    0.43
    ্কৃত
    0.42
    imgInit
    0.41
    ▥
    0.41
    POSITIVE LOGITS
    S
    0.49
    E
    0.45
    𝐄
    0.44
     bege
    0.44
     out
    0.44
    U
    0.43
     gang
    0.43
     Embassy
    0.43
     so
    0.42
     doen
    0.42
    Activations Density 0.023%

    No Known Activations