© 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. 61919
    Prev
    Next
    INDEX
    Explanations

    website content, visual media

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

    online content creation and services

    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
    jaar
    0.52
    geoLocation
    0.44
    stück
    0.43
    м
    0.43
    oción
    0.43
     tersedia
    0.42
     אוי
    0.42
    ostructures
    0.41
    zus
    0.41
    gerät
    0.40
    POSITIVE LOGITS
     पाहून
    0.52
     gently
    0.51
     reprendre
    0.50
    রাধ
    0.50
    잌
    0.48
    வ்வாறு
    0.47
     win
    0.46
     Dean
    0.46
     glyc
    0.46
     neatly
    0.46
    Activations Density 0.000%

    No Known Activations