© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3868
    Prev
    Next
    INDEX
    Explanations

    slightly different

    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
    anat
    2.97
     नक्षत्र
    2.95
    eniz
    2.88
    𝑠
    2.87
    anon
    2.86
    ceptron
    2.84
    颢
    2.82
    raad
    2.74
     aceea
    2.72
    嗘
    2.72
    POSITIVE LOGITS
     off
    2.37
    off
    2.37
    OFF
    2.24
    born
    2.23
     OFF
    2.11
    ced
    2.06
    Off
    2.01
    ty
    2.00
     setImage
    1.99
     Off
    1.96
    Activations Density 0.014%

    No Known Activations