© 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. 166252
    Prev
    Next
    INDEX
    Explanations

    back in the league

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

    to reach or look

    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
     (
    0.49
    <0xE3>
    0.46
     KeyEvent
    0.46
    ངས་
    0.43
     Registry
    0.42
     Client
    0.42
    ――
    0.42
    Ж
    0.42
    凡
    0.42
    真正
    0.41
    POSITIVE LOGITS
     améli
    0.61
     améliorer
    0.55
     amélior
    0.52
    aporation
    0.51
     mengurangi
    0.49
     свадь
    0.49
     étudier
    0.48
     éduc
    0.48
     menyelesaikan
    0.48
     romances
    0.48
    Activations Density 0.000%

    No Known Activations