© 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. 11967
    Prev
    Next
    INDEX
    Explanations

    Portuguese, pottery, afore, hosiery, 무

    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
    ष्कार
    2.88
    मेल
    2.71
     bekom
    2.63
     considère
    2.61
    জিওথের
    2.60
    स्कार
    2.52
     byť
    2.52
    떳
    2.49
    ετε
    2.49
    immung
    2.48
    POSITIVE LOGITS
    er
    2.63
    eram
    2.37
    
    2.37
     AA
    2.32
    ous
    2.30
    aught
    2.28
    mals
    2.27
    an
    2.22
    erden
    2.19
     K
    2.17
    Activations Density 0.003%

    No Known Activations