© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4507
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aldo
    1.42
     Aircraft
    1.38
     Ольга
    1.38
     Olsen
    1.38
     restlessness
    1.36
     Airways
    1.36
     Roc
    1.36
    ا
    1.34
     Олег
    1.29
     Arne
    1.29
    POSITIVE LOGITS
    Shah
    0.65
     Shah
    0.61
    shah
    0.59
    hafte
    0.56
    hua
    0.55
     Faw
    0.54
     trình
    0.49
    PEM
    0.48
     TAN
    0.46
    ğan
    0.45
    Activations Density 0.070%

    No Known Activations