© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    practice makes perfect

    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
    er
    2.36
     Miners
    2.11
    iquette
    1.98
     Depot
    1.98
    ibut
    1.96
    r
    1.93
     علمی
    1.93
    -”
    1.92
     الابتدائي
    1.91
    اه
    1.90
    POSITIVE LOGITS
    ங்கிணை
    2.67
    дается
    2.65
     actionMode
    2.46
    性の
    2.35
    𝘖
    2.26
    вания
    2.26
    Uppercase
    2.26
    WithOwner
    2.26
    性
    2.25
    NotNull
    2.24
    Activations Density 0.033%

    No Known Activations