© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211591
    Prev
    Next
    INDEX
    Explanations

    prepositions for multiple languages

    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_40_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
    accurate
    0.42
    <unused9>
    0.41
    Qs
    0.39
    captivity
    0.39
     unauthorized
    0.39
    hearted
    0.38
    ataan
    0.38
     Unauthorized
    0.38
    ৫৮
    0.38
     Ελλά
    0.37
    POSITIVE LOGITS
     для
    0.49
     für
    0.48
     sadece
    0.43
    для
    0.42
     pentru
    0.42
    ποτε
    0.42
     ①
    0.41
     untuk
    0.41
     offrir
    0.41
     για
    0.40
    Activations Density 0.000%

    No Known Activations