© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12891
    Prev
    Next
    INDEX
    Explanations

    table headers and structured lists

    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
    م
    3.49
    ের
    2.50
    ০
    2.49
    m
    2.43
    ي
    2.43
    igence
    2.42
    ം
    2.41
    یه
    2.40
    ာ
    2.39
    ுக்கு
    2.39
    POSITIVE LOGITS
    ="#!"
    2.58
    즘
    2.18
     सामील
    2.15
    Credential
    2.14
    answ
    2.10
    SLICE
    2.08
    hashTree
    2.06
    enterprise
    2.03
    djangoproject
    2.00
    experiments
    1.97
    Activations Density 0.009%

    No Known Activations