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-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1888
    Prev
    Next
    INDEX
    Explanations

    programming code context

    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_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
    ﯿ
    1.88
    Einstellungen
    1.84
    rons
    1.82
    siz
    1.80
     amps
    1.74
    songs
    1.70
    طان
    1.70
     transfected
    1.67
    pubescens
    1.66
    syair
    1.65
    POSITIVE LOGITS
    า
    2.70
    ش
    2.63
    ो
    2.44
    り
    2.30
    나
    2.30
    きました
    2.27
    یں
    2.25
    てください
    2.19
    ž
    2.17
    ש
    2.17
    Activations Density 0.786%

    No Known Activations