© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    cos(angle)

    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
    𝐫
    3.07
    ","",
    2.48
     saj
    2.46
    Central
    2.37
    𝐧
    2.32
    𝐡
    2.32
    memberNameLink
    2.22
    ेक्षित
    2.22
    """
    2.17
    𝐥
    2.17
    POSITIVE LOGITS
    ان
    2.37
     doodles
    2.34
    ahertz
    2.32
     exclamation
    2.32
    ேஷ்
    2.30
    에
    2.29
    に
    2.23
     autocomplete
    2.20
     गुना
    2.19
    搡
    2.18
    Activations Density 0.000%

    No Known Activations