© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    build process

    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
    पहर
    3.05
    ियोजना
    2.74
    ंपरा
    2.56
    MONGO
    2.48
    oretical
    2.39
    ঙ
    2.39
    प्ताह
    2.34
    त्कार
    2.31
    insertBefore
    2.27
    પાસ
    2.25
    POSITIVE LOGITS
    s
    4.95
    t
    3.98
    sı
    3.47
    tin
    3.25
    shen
    3.20
    suits
    3.08
    sberg
    3.07
    sad
    2.95
    tica
    2.94
    ture
    2.93
    Activations Density 0.008%

    No Known Activations