© 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. 114985
    Prev
    Next
    INDEX
    Explanations

    technology and its impact

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

    technology related concepts and terms

    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
    மாக
    0.80
    िंग
    0.80
     on
    0.79
    <unused29>
    0.78
    ，
    0.78
    యిత
    0.77
    이었
    0.76
    ных
    0.74
    ным
    0.74
    ،
    0.73
    POSITIVE LOGITS
    <0x80>
    1.20
    }
    1.09
    c
    1.05
    h
    1.04
    )
    1.03
    _
    1.02
    H
    0.99
     a
    0.97
    '
    0.93
    0
    0.92
    Activations Density 0.057%

    No Known Activations