© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    trash and Rock

    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
    𝕊
    1.81
    prestations
    1.70
    𝚃
    1.65
    नाती
    1.64
    keyValue
    1.59
    Connections
    1.53
    𝙏
    1.52
     régimen
    1.52
    𝙍
    1.51
     vínculo
    1.51
    POSITIVE LOGITS
    e
    2.18
    加坡
    1.91
     （
    1.91
    tub
    1.76
    hots
    1.73
    tart
    1.67
     ('
    1.67
    oze
    1.67
     (?)
    1.66
    sne
    1.66
    Activations Density 0.002%

    No Known Activations