© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    IP addresses and ports

    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
    DEFGHIJKLMNOP
    3.13
    o
    2.63
    ので
    2.57
    ו
    2.53
    e
    2.53
    tive
    2.50
    า
    2.46
    a
    2.46
    ු
    2.45
    tio
    2.44
    POSITIVE LOGITS
    乎
    2.06
     stop
    1.93
     stationary
    1.86
     stretch
    1.84
    heastern
    1.79
     safari
    1.76
     citizenship
    1.76
    पे
    1.75
     stretched
    1.74
     closed
    1.74
    Activations Density 0.030%

    No Known Activations