© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 477
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    __
    1.23
    ’
    1.22
    |.|
    1.11
    Ž
    1.11
    TRAILING
    1.07
    אות
    1.06
    MSBuildTools
    1.06
    quality
    1.05
    ][_
    1.05
    Quality
    1.04
    POSITIVE LOGITS
    ्ञ
    1.74
    ಾಗಲೇ
    1.65
    লন
    1.60
    adays
    1.57
     floc
    1.49
    varande
    1.44
    sframe
    1.43
    ହା
    1.42
    aday
    1.42
    slick
    1.42
    Activations Density 2.295%

    No Known Activations