© 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. 2079
    Prev
    Next
    INDEX
    Explanations

    route attribute ending

    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
    ர்
    1.75
     cPix
    1.65
     CAUSED
    1.60
    萏
    1.57
     неу
    1.54
    CycleOffset
    1.54
    ᕋ
    1.54
     HUOBI
    1.53
    DISCUSSION
    1.53
    잍
    1.53
    POSITIVE LOGITS
    GB
    1.43
    B
    1.32
    ement
    1.30
    F
    1.30
    J
    1.30
    way
    1.29
     '
    1.29
    rentice
    1.26
    ened
    1.26
    ening
    1.25
    Activations Density 0.134%

    No Known Activations