© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11487
    Prev
    Next
    INDEX
    Explanations

    Kp = Proportional Gain

    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
    CommandBuffer
    2.62
    ંદ
    2.60
    AUX
    2.58
    aux
    2.57
    uptools
    2.53
    ̍
    2.49
    оні
    2.48
     errorHandler
    2.45
    ++++++++++++++++
    2.44
     boycot
    2.44
    POSITIVE LOGITS
    ly
    3.55
    nya
    3.08
    ness
    2.48
    了
    2.40
    다는
    2.36
    ت
    2.26
    다고
    2.24
    ry
    2.22
    ة
    2.17
    ときは
    2.15
    Activations Density 0.037%

    No Known Activations