© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27952
    Prev
    Next
    INDEX
    Explanations

    date activities

    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_16_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
     Toxicology
    0.60
     Epidemiology
    0.60
    с
    0.59
    ecology
    0.58
    ح
    0.57
     Mortgage
    0.56
    RoleId
    0.54
     Ecology
    0.53
    бри
    0.52
    കരണ
    0.52
    POSITIVE LOGITS
     restaurants
    0.63
     рестора
    0.60
    デート
    0.59
     vibhav
    0.55
     더
    0.54
    énom
    0.52
     yě
    0.52
     chicks
    0.51
     diners
    0.51
    iname
    0.51
    Activations Density 0.036%

    No Known Activations