© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1594
    Prev
    Next
    INDEX
    Explanations

    building levels and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     precisión
    1.01
     недели
    1.00
    这篇文章
    0.99
     publicó
    0.98
     provincias
    0.96
     erit
    0.96
     速
    0.96
     grits
    0.95
     semana
    0.95
    囝
    0.94
    POSITIVE LOGITS
     staircase
    3.02
     balcony
    2.84
     stairs
    2.76
     rooftop
    2.76
     stair
    2.75
     balconies
    2.66
     mezzanine
    2.56
     roof
    2.56
     stairway
    2.55
     floors
    2.55
    Activations Density 0.767%

    No Known Activations