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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8446
    Prev
    Next
    INDEX
    Explanations

    `and` followed by a noun

    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_12_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
    ر
    0.99
    ا
    0.95
    л
    0.85
    i
    0.84
    おそらく
    0.82
    с
    0.82
    illiant
    0.81
    в
    0.81
    ه
    0.81
    ج
    0.80
    POSITIVE LOGITS
     Provinz
    0.84
     flanked
    0.81
     female
    0.76
     ámbito
    0.76
     collaboratively
    0.75
     roaming
    0.75
     one
    0.74
    वाले
    0.74
     tú
    0.74
     detectives
    0.74
    Activations Density 0.000%

    No Known Activations