© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36796
    Prev
    Next
    INDEX
    Explanations

    code creation and initializers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     Nab
    0.44
     slashed
    0.43
     plucked
    0.43
    \}=
    0.43
    ói
    0.42
     shifted
    0.41
    -->
    0.40
    ockey
    0.40
     unacceptable
    0.40
    টিয়ে
    0.40
    POSITIVE LOGITS
    ({
    0.42
    ,{
    0.42
    Goals
    0.38
    骷
    0.38
     வைத்திருக்க
    0.37
    {&
    0.37
    precision
    0.36
    মধ্য
    0.36
    《
    0.36
    gl
    0.35
    Activations Density 0.028%

    No Known Activations