© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47337
    Prev
    Next
    INDEX
    Explanations

    New York

    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_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
     phép
    0.50
     ওয়েবসাইট
    0.44
     propriedades
    0.44
     útiles
    0.44
    可以使用
    0.43
    ቁ
    0.43
     usados
    0.41
    عيب
    0.40
     incentiv
    0.40
    धन
    0.40
    POSITIVE LOGITS
    ity
    0.46
    でした
    0.46
    eda
    0.44
     biblical
    0.42
    ました
    0.42
    itudinal
    0.42
     honoring
    0.42
    küm
    0.42
    na
    0.42
    💔
    0.41
    Activations Density 0.009%

    No Known Activations