© 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. 155468
    Prev
    Next
    INDEX
    Explanations

    time, posts, gravity, brand, spent

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

    data analysis and programming

    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
    are
    0.59
     of
    0.50
     Emp
    0.50
    ],
    0.49
     Audi
    0.48
     are
    0.47
    ities
    0.47
     enthusiasm
    0.45
    ہیں
    0.45
    ,
    0.44
    POSITIVE LOGITS
    okkh
    0.49
    skjaer
    0.47
     mengenal
    0.47
    ያን
    0.47
    ান্ডার
    0.46
    য়ান
    0.45
    㙅
    0.45
    рал
    0.45
    괄
    0.45
    categorias
    0.45
    Activations Density 0.002%

    No Known Activations