© 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. 14010
    Prev
    Next
    INDEX
    Explanations

    numbers, quantifiers, possessives

    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
     your
    0.45
     einer
    0.43
     Royal
    0.42
    able
    0.42
     Southwest
    0.42
     unserer
    0.41
    \
    0.41
     Jeep
    0.41
     personn
    0.40
    ♥♥
    0.40
    POSITIVE LOGITS
     ones
    1.10
    它们
    0.71
    のもの
    0.71
     theirs
    0.67
     тях
    0.67
    もの
    0.64
     hacerlo
    0.63
     quelli
    0.63
    ものが
    0.62
    它們
    0.61
    Activations Density 0.204%

    No Known Activations