© 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. 244324
    Prev
    Next
    INDEX
    Explanations

    here all

    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
     khảo
    0.52
     terminating
    0.48
    aaaa
    0.48
     WHICH
    0.48
    浼
    0.47
    pass
    0.47
    ρ
    0.46
     allow
    0.46
     passed
    0.46
    passed
    0.46
    POSITIVE LOGITS
    ى
    0.58
     beginnetje
    0.45
    斌
    0.43
     HttpClient
    0.42
     Zell
    0.42
    aprendizaje
    0.42
    سين
    0.42
    unton
    0.42
     Zellen
    0.42
     Marr
    0.41
    Activations Density 0.000%

    No Known Activations