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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6984
    Prev
    Next
    INDEX
    Explanations

    phrases in quotes or explanations

    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
    कृपया
    0.47
    टा
    0.47
    DAMAGE
    0.46
    ]$
    0.43
    elens
    0.43
    ле
    0.43
    ᅦ
    0.42
    ค้า
    0.42
    भ
    0.41
     מב
    0.41
    POSITIVE LOGITS
     ducks
    0.45
     manipulate
    0.44
    derabad
    0.44
     indict
    0.43
     UICtrl
    0.43
     manip
    0.42
     وبين
    0.42
     suspense
    0.42
    мани
    0.41
     Kotor
    0.41
    Activations Density 0.013%

    No Known Activations