© 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. 53106
    Prev
    Next
    INDEX
    Explanations

    transactions and communications

    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
    AdType
    0.47
    笳
    0.45
    weathermap
    0.43
    Interstitial
    0.43
    addField
    0.43
    بین
    0.42
    adn
    0.42
    apayati
    0.42
    вающий
    0.41
     մի
    0.41
    POSITIVE LOGITS
     jederzeit
    0.49
     directors
    0.46
     W
    0.45
     viime
    0.44
     cumpr
    0.43
     revisions
    0.43
     films
    0.42
     customers
    0.42
     familiares
    0.42
    gebnisse
    0.42
    Activations Density 0.007%

    No Known Activations