© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13714
    Prev
    Next
    INDEX
    Explanations

    lighthearted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     lighting
    1.22
     Lighting
    1.14
    Lighting
    1.11
     lights
    1.09
     lanterns
    0.96
     lamp
    0.95
    燈
    0.93
     lum
    0.89
    ه
    0.89
     lamps
    0.88
    POSITIVE LOGITS
    hearted
    1.17
    ings
    1.01
    heartedly
    1.00
    elijk
    0.97
    ješ
    0.94
    jährige
    0.93
    ቭ
    0.93
    imedia
    0.84
    fillna
    0.84
    years
    0.82
    Activations Density 0.039%

    No Known Activations