© 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. 2136
    Prev
    Next
    INDEX
    Explanations

    organization by sections

    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
    $^{
    3.29
    ग्विजय
    3.13
    
    3.01
    ঃখ
    3.01
    蜊
    2.99
    thel
    2.86
    दर्शिता
    2.77
    meri
    2.76
    skom
    2.72
    র্ঘট
    2.70
    POSITIVE LOGITS
    𝒊
    3.79
    𝒆
    3.67
    ੀ
    3.59
    𝒖
    3.47
    يّ
    3.45
    𝒔
    3.33
    </strong>
    3.26
    u
    3.25
    eted
    3.17
    ي
    3.07
    Activations Density 0.020%

    No Known Activations