© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62827
    Prev
    Next
    INDEX
    Explanations

    service offers in locations

    np_acts-logits-general · gemini-2.5-flash-lite

    math and grammar concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    നിന്ന്
    0.43
     તેથી
    0.42
    diri
    0.42
    ieval
    0.41
    シュ
    0.40
    šie
    0.40
    奥行
    0.39
    欳
    0.39
    டுவது
    0.39
    .],
    0.39
    POSITIVE LOGITS
     мо
    0.44
     подроб
    0.43
     Lucky
    0.42
    Lucky
    0.39
    详
    0.38
     Details
    0.37
     Learned
    0.36
     Assass
    0.36
    详细
    0.36
     उठे
    0.36
    Activations Density 0.007%

    No Known Activations