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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2597
    Prev
    Next
    INDEX
    Explanations

    Removed redundant or unnecessary text

    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_13_width_65k_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
    )
    1.27
    0
    1.01
    it
    1.00
    /
    0.93
    .
    0.91
    -
    0.88
    m
    0.85
    с
    0.82
    p
    0.82
    ).
    0.80
    POSITIVE LOGITS
     berbagai
    2.23
     çeşitli
    2.15
     다양한
    2.09
     sejumlah
    2.05
     zahlreichen
    2.04
     renowned
    1.98
     legendary
    1.93
     những
    1.92
     charismatic
    1.92
     numerose
    1.92
    Activations Density 0.836%

    No Known Activations