© 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. 36578
    Prev
    Next
    INDEX
    Explanations

    drive with, by famed

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

    circumstances and relations

    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
    </td>
    0.42
    yn
    0.40
    Up
    0.39
     Worldwide
    0.38
     Filing
    0.37
    VS
    0.37
     versus
    0.37
    সং
    0.37
     Central
    0.36
     Makers
    0.36
    POSITIVE LOGITS
    굉
    0.55
     longueur
    0.49
     uwagę
    0.49
    损害
    0.48
     obesidad
    0.48
     совокуп
    0.48
     circumst
    0.47
     një
    0.47
     circumstances
    0.46
     profondeur
    0.46
    Activations Density 0.000%

    No Known Activations