© 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. 245749
    Prev
    Next
    INDEX
    Explanations

    your favorite gifts

    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
     particulier
    0.51
    เมื่อ
    0.48
     stratum
    0.47
    ietro
    0.47
    醜
    0.46
     fijn
    0.45
     darken
    0.44
     surtout
    0.44
     e
    0.43
     inscrit
    0.43
    POSITIVE LOGITS
    ăzi
    0.48
    अपना
    0.48
    하니
    0.48
    ленность
    0.45
     توصل
    0.44
     canales
    0.43
    लोग
    0.42
    🚶
    0.42
    푼
    0.41
    ми
    0.41
    Activations Density 0.001%

    No Known Activations