© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    don't say anything

    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
    der
    1.82
     m
    1.67
    ya
    1.54
    </em>
    1.50
     fl
    1.45
     rich
    1.41
    j
    1.41
     -
    1.39
    </h1>
    1.38
    .
    1.38
    POSITIVE LOGITS
    궪
    2.78
    मतौर
    2.78
     γίνει
    2.73
    लिसिस
    2.71
    お子
    2.67
    뺻
    2.65
    鏄
    2.63
     изпол
    2.61
    뿯
    2.58
    ᐱ
    2.57
    Activations Density 0.001%

    No Known Activations