© 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. 12167
    Prev
    Next
    INDEX
    Explanations

    Fiverr services

    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
    hoot
    2.39
    eka
    2.20
    CDATA
    2.18
    ViewGroup
    2.13
    assertRaises
    2.10
    இந்த
    2.08
    eko
    2.08
    ச
    2.06
    는
    2.05
    eating
    2.05
    POSITIVE LOGITS
     sake
    3.25
    geries
    3.21
     starters
    2.94
    gery
    2.87
     posterity
    2.74
     betterment
    2.73
     purposes
    2.64
     Sake
    2.59
    gie
    2.52
    genza
    2.50
    Activations Density 0.236%

    No Known Activations