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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 664
    Prev
    Next
    INDEX
    Explanations

    mythology nor superstitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     människ
    1.59
    硌
    1.54
    認為
    1.54
     feita
    1.52
     nemo
    1.52
    认为
    1.49
     branco
    1.49
    諳
    1.49
     fábrica
    1.48
    imentary
    1.47
    POSITIVE LOGITS
     increase
    2.40
    increase
    2.22
     increasing
    2.20
    Increase
    2.12
     increases
    2.10
     decrease
    2.08
     decreases
    2.08
     Increase
    2.06
     decreasing
    2.06
     increased
    1.98
    Activations Density 0.666%

    No Known Activations