© 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. 11401
    Prev
    Next
    INDEX
    Explanations

    mountain names

    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
    躇
    2.93
    đồng
    2.64
    ilustración
    2.50
    origData
    2.50
     бур
    2.49
    িক
    2.43
     símbolos
    2.43
     suaves
    2.42
    \}
    2.40
    tableLayoutPanel
    2.40
    POSITIVE LOGITS
    rest
    2.94
     rest
    2.84
    sman
    2.73
     UIT
    2.69
    enance
    2.67
    uptools
    2.53
    ريس
    2.53
    s
    2.50
    spot
    2.48
    ামুটি
    2.47
    Activations Density 0.006%

    No Known Activations