© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201915
    Prev
    Next
    INDEX
    Explanations

    biological changes and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    id
    0.44
     과
    0.44
     GNU
    0.43
     jika
    0.43
     lalu
    0.43
     기존
    0.43
     ঢে
    0.43
     및
    0.43
     बताती
    0.42
     Kein
    0.41
    POSITIVE LOGITS
    Mart
    0.42
    [{}\
    0.42
    ס
    0.42
     principally
    0.41
    Ó
    0.41
    Warm
    0.41
    сима
    0.41
    تام
    0.41
    Atlas
    0.41
     beggars
    0.41
    Activations Density 0.008%

    No Known Activations