© 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. 13003
    Prev
    Next
    INDEX
    Explanations

    length, effort, complexity, formality

    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
     undamaged
    2.35
     已
    2.31
    aphazard
    2.26
    酛
    2.19
    .~(\
    2.19
    noDB
    2.18
     전류
    2.18
    ṓ
    2.17
     unsuitable
    2.15
    suitable
    2.13
    POSITIVE LOGITS
    っていう
    2.37
     temos
    1.99
     coisas
    1.97
     tadi
    1.94
     fizemos
    1.94
    quela
    1.91
     itu
    1.90
     mensen
    1.87
     gitu
    1.85
     kita
    1.84
    Activations Density 0.886%

    No Known Activations