© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 179229
    Prev
    Next
    INDEX
    Explanations

    location, genre, fast, peak

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

    app serves location services

    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
    )}$.
    0.45
    룀
    0.45
    )}$,
    0.44
    せ
    0.44
    }}$;
    0.44
    }}$,
    0.44
    }$,
    0.42
    öre
    0.42
    rö
    0.42
    øk
    0.42
    POSITIVE LOGITS
     Hua
    0.54
    4
    0.54
     ऊंचाई
    0.54
     hua
    0.51
    はこの
    0.51
    টসঅ্যাপ
    0.51
     Xiang
    0.50
     kucing
    0.50
     Creed
    0.50
     झर
    0.49
    Activations Density 0.001%

    No Known Activations