© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 48840
    Prev
    Next
    INDEX
    Explanations

    conditions affecting state or understanding

    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
     heady
    0.44
     뜨
    0.44
     flexible
    0.43
     높은
    0.43
    onaut
    0.43
     rewarding
    0.42
     에너지
    0.42
    writeFile
    0.42
    urgical
    0.41
     adaptable
    0.41
    POSITIVE LOGITS
     Authentication
    0.61
    Authentication
    0.52
    Estimation
    0.51
     Gente
    0.51
    S
    0.51
     Estimation
    0.50
    ول
    0.49
     Administración
    0.49
    J
    0.49
    Hozz
    0.48
    Activations Density 0.028%

    No Known Activations