© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4065
    Prev
    Next
    INDEX
    Explanations

    sky and celestial bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     abrasive
    0.87
     thermoelectric
    0.85
     Jerm
    0.78
    靴
    0.78
     plastic
    0.76
     physical
    0.75
     thermo
    0.74
    塑
    0.74
     robotics
    0.73
     cryogenic
    0.73
    POSITIVE LOGITS
     sky
    2.07
     Sky
    1.67
    Sky
    1.66
    sky
    1.64
     skies
    1.64
     sunset
    1.60
     cielo
    1.58
     SKY
    1.48
     horizon
    1.47
     sunsets
    1.46
    Activations Density 0.322%

    No Known Activations