© 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. 209038
    Prev
    Next
    INDEX
    Explanations

    pairings following certain words

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

    build community or server

    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
     수는
    0.48
    estep
    0.48
    ત્રી
    0.47
    ωσης
    0.46
    িল্ল
    0.46
    sommets
    0.46
    ⵅ
    0.45
     foreclosure
    0.45
     collaborates
    0.45
     summits
    0.45
    POSITIVE LOGITS
    ة
    0.46
    as
    0.45
     konstant
    0.44
     totem
    0.43
    Tip
    0.42
     Tilt
    0.42
    0
    0.42
     simpat
    0.41
     fotografie
    0.40
    !
    0.40
    Activations Density 0.000%

    No Known Activations