© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110737
    Prev
    Next
    INDEX
    Explanations

    weekend trip plans

    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
     prevención
    0.50
    вшейся
    0.47
    <unused359>
    0.47
    럇
    0.46
     అనుమ
    0.46
    𝐧
    0.46
     поздрав
    0.45
    রোধ
    0.44
     состав
    0.44
    からない
    0.44
    POSITIVE LOGITS
    amme
    0.47
    al
    0.46
     leases
    0.45
    repetitions
    0.45
    ب
    0.45
    B
    0.44
     kuin
    0.44
     fournit
    0.43
    嶆
    0.41
     expressions
    0.41
    Activations Density 0.002%

    No Known Activations