© 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. 194868
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

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

    height, character, coolness

    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
    END
    0.57
    w
    0.49
    OU
    0.48
    r
    0.47
    ש
    0.46
    /
    0.46
    4
    0.45
    OURCE
    0.45
    ʽ
    0.45
    ÁN
    0.44
    POSITIVE LOGITS
     remplacer
    0.53
     แล้ว
    0.51
     sedangkan
    0.49
     Bhagavato
    0.48
    🎎
    0.47
     ngay
    0.46
    िलायंस
    0.46
     bangle
    0.46
     vissa
    0.45
     Sedangkan
    0.44
    Activations Density 0.001%

    No Known Activations