© 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. 83120
    Prev
    Next
    INDEX
    Explanations

    renovations and reporting

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

    takes, requires, estimate often followed by specifics

    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
     Ui
    0.49
     USE
    0.47
     The
    0.45
     This
    0.44
    0.44
     Client
    0.44
     Build
    0.43
     freq
    0.43
    <0x80>
    0.42
     ATI
    0.42
    POSITIVE LOGITS
    住院
    0.47
     diosa
    0.47
    കൊണ്ട്
    0.46
     renovations
    0.45
    والفقار
    0.44
     transformasi
    0.44
     cartoonist
    0.43
     миллиар
    0.43
     jiwa
    0.42
     баскет
    0.42
    Activations Density 0.001%

    No Known Activations