© 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. 15-GEMMASCOPE-2-RES-262K
    7. 70067
    Prev
    Next
    INDEX
    Explanations

    surface temperature climate magnetic

    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_15_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
     setan
    0.91
    婊
    0.89
     europeos
    0.89
    involved
    0.88
     españoles
    0.85
    world
    0.80
    asında
    0.79
    versed
    0.79
    Europe
    0.78
    competitive
    0.76
    POSITIVE LOGITS
     precipitation
    2.01
    咎
    1.90
     kinetic
    1.87
     frame
    1.86
     tissues
    1.86
     motions
    1.86
     evacuation
    1.85
     rainfall
    1.85
    mia
    1.83
     heat
    1.83
    Activations Density 0.007%

    No Known Activations