© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12884
    Prev
    Next
    INDEX
    Explanations

    grandmother

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    স্ফ
    0.61
     ஏற்படுகிறது
    0.61
    aphor
    0.58
    tey
    0.55
     avenues
    0.54
    ❆
    0.54
     เต
    0.54
    遨
    0.53
    UpInside
    0.53
    摧
    0.53
    POSITIVE LOGITS
    lant
    0.55
     grandmother
    0.52
     Buzz
    0.52
     buzz
    0.51
    人人
    0.51
     waited
    0.50
    clare
    0.50
     Granny
    0.49
     grandparent
    0.49
    ಗರ
    0.48
    Activations Density 0.000%

    No Known Activations