© 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. 62419
    Prev
    Next
    INDEX
    Explanations

    maintaining secrecy or confidentiality

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

    relativity, raising reviewer, localized fires

    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
    িক্ষে
    0.58
     விமானங்கள்
    0.51
     âmbito
    0.51
     ہونا
    0.50
     εισ
    0.50
    獪
    0.50
     bicicletas
    0.50
    同比
    0.50
     nasze
    0.49
    DataXYZ
    0.49
    POSITIVE LOGITS
    ir
    0.50
    WIL
    0.46
    EN
    0.46
     i
    0.45
     written
    0.45
    SJ
    0.45
    ิ
    0.44
     BO
    0.44
    ER
    0.43
    ac
    0.43
    Activations Density 0.000%

    No Known Activations