© 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. 51511
    Prev
    Next
    INDEX
    Explanations

    analysis of system charges

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

    fitting objects

    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
     viser
    0.47
     passou
    0.47
    ji
    0.46
    f
    0.46
    e
    0.46
    inin
    0.44
    x
    0.43
    fo
    0.42
    fz
    0.42
     constable
    0.41
    POSITIVE LOGITS
     アー
    0.47
     तैर
    0.47
     任
    0.47
    堹
    0.47
    stering
    0.46
     沈
    0.46
    wnież
    0.46
    нок
    0.45
     হিন্দি
    0.45
    Ｖ
    0.45
    Activations Density 0.000%

    No Known Activations