© 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. 21417
    Prev
    Next
    INDEX
    Explanations

    residence or location

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

    objects and concepts

    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
     чего
    0.48
     sämt
    0.41
     및
    0.40
     протягом
    0.40
    /
    0.40
     любых
    0.40
     compliment
    0.39
    +
    0.39
    的能力
    0.38
    albeit
    0.38
    POSITIVE LOGITS
     Leningrad
    0.46
     त्यासाठी
    0.46
    akkhati
    0.46
    只好
    0.44
     मोठा
    0.44
     Dokl
    0.43
     Leser
    0.42
     Chac
    0.41
     प्रोफेसर
    0.41
     டாக்டர்
    0.41
    Activations Density 0.002%

    No Known Activations