© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3680
    Prev
    Next
    INDEX
    Explanations

    beginning of tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    κρα
    2.67
    sheet
    2.59
     fico
    2.57
    睺
    2.52
    
    2.44
    给予
    2.43
    佗
    2.35
    toEqual
    2.32
    杓
    2.32
     bầu
    2.32
    POSITIVE LOGITS
    ্ধু
    3.16
    엠
    3.01
    strument
    2.82
    spired
    2.82
    ruptedException
    2.69
    frastructure
    2.69
    ुस्तान
    2.67
    erv
    2.61
    besondere
    2.61
    蔽
    2.56
    Activations Density 0.239%

    No Known Activations