© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64741
    Prev
    Next
    INDEX
    Explanations

    often, popular, frequent

    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
    ஞ்சு
    0.44
     internazionale
    0.43
     internacional
    0.42
    ból
    0.42
    પૂર્ણ
    0.42
     livelihoods
    0.41
     Required
    0.41
    ت
    0.40
     yea
    0.40
    tól
    0.40
    POSITIVE LOGITS
    Grav
    0.44
    hatiti
    0.43
    Data
    0.42
    Согласно
    0.42
    Ainsi
    0.42
     रोमांच
    0.42
     데이터를
    0.42
    Bats
    0.42
     служит
    0.42
     Goliath
    0.42
    Activations Density 0.008%

    No Known Activations