Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 86
    Prev
    Next
    INDEX
    Explanations

    price, cost, monetary value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ně
    0.81
     Hø
    0.78
    jor
    0.77
     سه
    0.77
    sp
    0.77
     Nej
    0.75
     Т
    0.74
     Rö
    0.74
     จ
    0.74
    nek
    0.74
    POSITIVE LOGITS
     unarmed
    1.10
     anthocyan
    1.09
     octahedral
    1.05
     acetaldehyde
    1.03
     unseen
    1.02
     timid
    0.98
     spectrophot
    0.95
     acetonitrile
    0.95
     downregulated
    0.95
     piecewise
    0.94
    Activations Density 0.000%

    No Known Activations