© 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. 242495
    Prev
    Next
    INDEX
    Explanations

    saving money

    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
    ERGY
    0.48
    ೆ
    0.46
    ewnętr
    0.44
    ніх
    0.43
     mie
    0.43
    APPY
    0.43
    تان
    0.43
    िकन
    0.42
    вало
    0.42
    żd
    0.42
    POSITIVE LOGITS
     champion
    0.49
     district
    0.46
     దక్షిణ
    0.44
    vadipine
    0.43
     disabilities
    0.43
     Beijing
    0.42
    銅
    0.42
     previous
    0.42
    quisites
    0.42
    BLE
    0.42
    Activations Density 0.000%

    No Known Activations