© 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. 17529
    Prev
    Next
    INDEX
    Explanations

    werden können

    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
     decolor
    0.65
     investig
    0.61
     integrand
    0.57
     digoxin
    0.55
    t
    0.54
     inactiv
    0.53
     исследователь
    0.52
     inpatient
    0.52
     investigar
    0.52
     ceg
    0.51
    POSITIVE LOGITS
    政府
    0.44
    梦
    0.44
    认识
    0.43
    密码
    0.43
    Amy
    0.43
     MODELS
    0.43
    मताओं
    0.43
    悰
    0.42
    धील
    0.42
     }^{
    0.41
    Activations Density 0.000%

    No Known Activations