© 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-16K
    7. 1206
    Prev
    Next
    INDEX
    Explanations

    animals

    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
     történ
    1.16
     manhood
    1.05
     Özellikle
    1.05
    ायला
    1.03
     hoa
    1.02
    ⏤
    1.00
     shootout
    0.96
     sebepler
    0.96
    aurants
    0.95
     fpr
    0.95
    POSITIVE LOGITS
     животных
    1.52
    dogs
    1.24
    0
    1.24
    animals
    1.23
     animais
    1.21
     animals
    1.20
    cat
    1.14
     hayvan
    1.13
     carcasses
    1.13
    fish
    1.11
    Activations Density 0.951%

    No Known Activations