© 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. 100983
    Prev
    Next
    INDEX
    Explanations

    interesting content niche topic

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

    various technical and descriptive phrases

    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
    見
    0.46
    હો
    0.46
    Setting
    0.46
    가
    0.45
    ने
    0.44
     mik
    0.43
     setNew
    0.43
     तपाईं
    0.42
    óm
    0.42
    5
    0.42
    POSITIVE LOGITS
    CurrentByte
    0.50
    䳕
    0.50
    financ
    0.48
    Throwable
    0.44
    ceği
    0.43
     eBooks
    0.43
     Financ
    0.43
    ExpressCheckout
    0.43
     economics
    0.42
    ciaux
    0.41
    Activations Density 0.001%

    No Known Activations