© 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. 55583
    Prev
    Next
    INDEX
    Explanations

    batch of, improved performance, outstanding pictures

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

    whale hunting

    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
     esim
    0.51
     tato
    0.50
     配
    0.50
     conceitos
    0.47
    ních
    0.47
     কথোপ
    0.46
     snad
    0.46
     escolher
    0.45
    handlungen
    0.45
    saus
    0.45
    POSITIVE LOGITS
    व
    0.53
    घा
    0.44
     ratepayers
    0.43
    समझ
    0.43
     Frenchman
    0.42
     verticals
    0.41
    न
    0.40
     recorded
    0.40
    밤
    0.40
     officers
    0.40
    Activations Density 0.000%

    No Known Activations