© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7574
    Prev
    Next
    INDEX
    Explanations

    System. or ;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     Ingersoll
    0.43
    放
    0.43
     मिळते
    0.43
     RESULTS
    0.42
     ENG
    0.41
    ENG
    0.41
     ALL
    0.41
    過
    0.41
     Vibes
    0.40
     Releases
    0.39
    POSITIVE LOGITS
    ños
    0.44
     días
    0.44
    ia
    0.44
    ী
    0.44
     आशंका
    0.43
    ewo
    0.43
    ooi
    0.43
    atoshi
    0.43
    ë
    0.42
    বাক
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.