© 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. 112551
    Prev
    Next
    INDEX
    Explanations

    long distance walks

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

    direct expression or reference

    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
    lán
    0.42
     frü
    0.42
     </
    0.40
     Mut
    0.40
     VIA
    0.40
    ዲ
    0.40
     Pf
    0.40
     ముఖ్య
    0.39
     Pour
    0.39
     Pois
    0.39
    POSITIVE LOGITS
    вался
    0.54
     chiesto
    0.54
    の名前
    0.54
    ῶ
    0.54
     perdu
    0.52
     desempen
    0.52
     começ
    0.52
    歓迎
    0.50
     наве
    0.50
    henden
    0.50
    Activations Density 0.000%

    No Known Activations