© 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. 53225
    Prev
    Next
    INDEX
    Explanations

    README file

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

    README.md files

    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
    τών
    0.52
     méthode
    0.50
     cannula
    0.50
     potencia
    0.50
    🩸
    0.50
    ्यूट
    0.49
     requête
    0.49
     보유
    0.49
     Record
    0.48
     decisive
    0.48
    POSITIVE LOGITS
     angesch
    0.62
    readme
    0.55
    ul
    0.51
    ي
    0.50
    jv
    0.50
     अराउंड
    0.49
    README
    0.49
     folders
    0.46
     readme
    0.46
     README
    0.45
    Activations Density 0.001%

    No Known Activations