© 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. 12197
    Prev
    Next
    INDEX
    Explanations

    Avengers

    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
     hề
    2.73
     états
    2.58
    ,\,
    2.57
     Pred
    2.52
    ियाँ
    2.50
    잎
    2.49
    र
    2.48
    ように
    2.47
    quiera
    2.45
    Mapped
    2.44
    POSITIVE LOGITS
    ات
    2.71
    "{
    2.59
    蝣
    2.41
    রাস
    2.37
    ns
    2.31
    페
    2.30
    래
    2.28
    rak
    2.25
    rrrr
    2.25
    க
    2.22
    Activations Density 0.010%

    No Known Activations