© 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. 12325
    Prev
    Next
    INDEX
    Explanations

    goldmines

    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
     guest
    1.74
    թ
    1.68
     paid
    1.67
    ра
    1.66
    త్
    1.66
    𝚍
    1.65
    Sc
    1.59
     спро
    1.58
    ال
    1.57
    randint
    1.57
    POSITIVE LOGITS
     ouvre
    2.59
    ières
    2.43
    sü
    2.42
    ल्टा
    2.40
    s
    2.39
    sı
    2.38
     magasiner
    2.37
    sia
    2.37
    ných
    2.34
     substrings
    2.32
    Activations Density 0.000%

    No Known Activations