© 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. 110892
    Prev
    Next
    INDEX
    Explanations

    online Vernon

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

    goals and targets

    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
     влас
    0.47
     North
    0.46
    )
    0.45
    ).
    0.45
     )
    0.44
     Owner
    0.44
     Younger
    0.44
    $).
    0.44
     LV
    0.42
    સ
    0.42
    POSITIVE LOGITS
    limiting
    0.62
    ຜະລິດຕ
    0.60
     guérir
    0.55
    seleccion
    0.54
    벚
    0.53
    printDialog
    0.52
    뗑
    0.52
    éria
    0.50
    onu
    0.49
    isDisabled
    0.49
    Activations Density 0.000%

    No Known Activations