© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10447
    Prev
    Next
    INDEX
    Explanations

    benefits

    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_13_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
    s
    2.75
    س
    2.50
    saint
    2.45
    t
    2.42
    ת
    2.35
    sack
    2.32
    ு
    2.30
    tion
    2.26
    ದ
    2.23
    tien
    2.20
    POSITIVE LOGITS
    gets
    2.48
    vol
    2.40
    বিষ্য
    2.37
    ynchronously
    2.15
    getting
    2.14
    theless
    2.13
    jorie
    2.11
    seguir
    2.11
    get
    2.10
    संधान
    2.08
    Activations Density 0.255%

    No Known Activations