© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    sculptural and business structures

    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
    ginger
    2.92
    ﺍ
    2.59
    yacute
    2.58
    𝗹
    2.53
    藹
    2.49
    𝘃
    2.48
    蛜
    2.48
    evice
    2.46
    ged
    2.45
    थमिक
    2.44
    POSITIVE LOGITS
    aston
    2.16
    <bos>
    1.93
     অফিসের
    1.92
    ّا
    1.91
    乜
    1.91
    nere
    1.91
    க
    1.88
    َّا
    1.86
     dehors
    1.84
     exploring
    1.84
    Activations Density 0.010%

    No Known Activations