© 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. 77173
    Prev
    Next
    INDEX
    Explanations

    kept shut

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

    offers improved or better

    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
     Bn
    0.53
     to
    0.47
     toolkit
    0.46
     P
    0.46
     Ernie
    0.46
     Ry
    0.46
     Soldier
    0.46
     CaCl
    0.46
     Tim
    0.46
     Pam
    0.46
    POSITIVE LOGITS
    ◈
    0.52
    了一眼
    0.49
    醴
    0.48
    Ranges
    0.47
    ีน
    0.47
    但是在
    0.46
     previewBuilder
    0.46
    ouwen
    0.45
    ኽ
    0.45
    mobilpay
    0.44
    Activations Density 0.003%

    No Known Activations