© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99023
    Prev
    Next
    INDEX
    Explanations

    personal or team contributions

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

    specialized or main focus

    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
    可以说是
    0.54
     paediatric
    0.52
    估计
    0.48
    이는
    0.48
    从而
    0.47
    লোকের
    0.47
     miệng
    0.45
    与
    0.45
    可以说
    0.45
    似乎
    0.45
    POSITIVE LOGITS
     purposely
    0.49
     persönlich
    0.46
     personalmente
    0.44
    і
    0.44
     personally
    0.43
     stets
    0.43
     Entscheidung
    0.42
     teamwork
    0.42
     Passion
    0.41
     massima
    0.41
    Activations Density 0.002%

    No Known Activations