© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14368
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and identities

    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_40_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
     postavlj
    0.44
     negozi
    0.43
     okup
    0.42
     jaanu
    0.42
     इंत
    0.41
     paiement
    0.41
    ⵓ
    0.41
     beachfront
    0.41
     zdoby
    0.40
    ┙
    0.40
    POSITIVE LOGITS
     Properties
    1.00
     properties
    0.99
    Properties
    0.96
     propriedades
    0.90
    properties
    0.89
     associativity
    0.89
     свойства
    0.88
     commutative
    0.86
    定理
    0.84
     property
    0.84
    Activations Density 0.036%

    No Known Activations