© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8744
    Prev
    Next
    INDEX
    Explanations

    -ing, -ed, -able endings

    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
     APRIL
    1.45
     infuri
    1.33
     pensé
    1.33
     MLAs
    1.33
     demoral
    1.32
     jordan
    1.31
     Mozambique
    1.29
    愴
    1.29
     desir
    1.27
     spore
    1.27
    POSITIVE LOGITS
    ного
    1.91
    个
    1.34
    ών
    1.30
    تان
    1.30
    ુ
    1.29
    ный
    1.27
     uczni
    1.20
    的前提
    1.18
    하여
    1.15
    ت
    1.15
    Activations Density 0.086%

    No Known Activations