© 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. 186602
    Prev
    Next
    INDEX
    Explanations

    offering to people

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

    fill in the blanks

    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
     Treatment
    0.47
     Guest
    0.46
     Champion
    0.46
     Century
    0.45
     Surface
    0.45
     Finals
    0.45
     Decade
    0.44
    轱
    0.44
     Officer
    0.44
     Agent
    0.43
    POSITIVE LOGITS
     insulators
    0.49
     عاي
    0.47
     bessere
    0.46
    instruments
    0.46
    amélioration
    0.46
     sustent
    0.45
     cadenas
    0.45
    bigcup
    0.45
    هن
    0.45
     agrand
    0.44
    Activations Density 0.000%

    No Known Activations