© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43263
    Prev
    Next
    INDEX
    Explanations

    disease, programming, calculation

    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
    ப்ட
    0.42
    pv
    0.42
    кри
    0.41
    cv
    0.39
    Ț
    0.39
    М
    0.38
    æ
    0.38
    隼
    0.38
    poque
    0.37
    dana
    0.37
    POSITIVE LOGITS
    !,
    0.46
     sugary
    0.44
     invertebrate
    0.42
     carbohydrate
    0.41
     legume
    0.41
     caloric
    0.41
     amelior
    0.40
     allere
    0.40
     hamster
    0.40
     ribbed
    0.40
    Activations Density 0.004%

    No Known Activations