© 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. 243192
    Prev
    Next
    INDEX
    Explanations

    advertising jobs

    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
    -
    0.46
     Дже
    0.45
     сві
    0.44
     mengandung
    0.44
     simonsen
    0.43
    gen
    0.43
     پہنچ
    0.43
     जानते
    0.42
     bright
    0.42
     pemilihan
    0.41
    POSITIVE LOGITS
    }°
    0.51
    數
    0.49
    喿
    0.48
     ngủ
    0.48
    琹
    0.48
    깆
    0.47
    గ్ర
    0.47
    ভাষ
    0.46
    생활
    0.46
    ства
    0.46
    Activations Density 0.000%

    No Known Activations