© 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. 41603
    Prev
    Next
    INDEX
    Explanations

    words and phrases

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

    rewording phrases

    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
     -
    0.64
    u
    0.57
    ling
    0.54
    ☻
    0.52
    BERG
    0.52
    semble
    0.52
    ladesh
    0.52
    lia
    0.51
    -
    0.51
    ett
    0.50
    POSITIVE LOGITS
     كلمات
    0.87
    一句
    0.83
     الفاظ
    0.82
     كلام
    0.80
     frases
    0.74
     phrases
    0.71
     utterances
    0.71
     வசன
    0.71
     言
    0.70
     வார்த்த
    0.69
    Activations Density 0.069%

    No Known Activations