© 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-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14893
    Prev
    Next
    INDEX
    Explanations

    France

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
    ENIDO
    0.73
     时尚
    0.61
     名前
    0.59
     թվական
    0.57
     fhould
    0.56
     Objekte
    0.55
    
    0.55
    িয়
    0.54
    Gen
    0.54
     વ
    0.53
    POSITIVE LOGITS
     type
    0.68
     equalizer
    0.65
     method
    0.61
     bug
    0.61
     pest
    0.60
     cooling
    0.59
     never
    0.58
     target
    0.58
     device
    0.57
     bul
    0.57
    Activations Density 0.002%

    No Known Activations