© 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. 219188
    Prev
    Next
    INDEX
    Explanations

    runway ideas, Christmas between, hidden features

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

    standard formalities, bursts, history, conflict

    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
    انون
    0.54
    按下
    0.51
    ΕΣ
    0.51
     教育
    0.48
    ıp
    0.47
     regained
    0.46
    钬
    0.46
     கல்
    0.46
     வே
    0.46
    વાન
    0.45
    POSITIVE LOGITS
    an
    0.53
     scrape
    0.49
    fond
    0.46
     masque
    0.45
    c
    0.45
     fond
    0.44
     lookup
    0.43
    om
    0.43
     They
    0.43
    in
    0.43
    Activations Density 0.001%

    No Known Activations