© 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-262K
    7. 53173
    Prev
    Next
    INDEX
    Explanations

    based on

    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_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
     ngũ
    0.46
     erreichen
    0.44
     utbild
    0.43
     হইয়৷
    0.43
     Sgt
    0.42
    បញ្ចប់
    0.42
     conseils
    0.42
     Feuerwehr
    0.42
    EDUC
    0.42
     인한
    0.41
    POSITIVE LOGITS
     любые
    0.51
    йл
    0.46
    .
    0.45
    ↵↵
    0.44
     exchange
    0.43
    uslararası
    0.43
    (
    0.43
     sooner
    0.42
     secretary
    0.41
    दा
    0.41
    Activations Density 0.008%

    No Known Activations