© 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. 208597
    Prev
    Next
    INDEX
    Explanations

    drugs, help, structure, teachings, carrying

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

    determined times and relate to

    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
     c
    0.47
     proposing
    0.46
    分离
    0.45
     동안
    0.45
     خز
    0.44
     קר
    0.44
     λα
    0.43
     इच्छा
    0.43
     nodig
    0.43
     ৭৭
    0.42
    POSITIVE LOGITS
    ет
    0.51
    de
    0.49
    明らか
    0.49
    fug
    0.47
    et
    0.46
    ř
    0.46
    nik
    0.46
    sud
    0.45
    excess
    0.45
    nati
    0.45
    Activations Density 0.001%

    No Known Activations