© 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. 150776
    Prev
    Next
    INDEX
    Explanations

    harming environment

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

    history continuation

    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
    िर
    0.49
    ら
    0.49
    றிவு
    0.49
    ணர்
    0.47
    ър
    0.46
    ėti
    0.45
    arı
    0.45
    会社
    0.44
    ́p
    0.44
    ственный
    0.44
    POSITIVE LOGITS
     нанесе
    0.52
     상당히
    0.50
    n
    0.49
     무
    0.48
    mun
    0.47
     نق
    0.47
    quirements
    0.46
    Mens
    0.46
    vacc
    0.46
    kval
    0.46
    Activations Density 0.000%

    No Known Activations