© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8856
    Prev
    Next
    INDEX
    Explanations

    location and state prepositions

    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_16_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
    ב
    0.70
    ק
    0.61
    د
    0.59
    ق
    0.59
    지
    0.59
    ו
    0.58
    خت
    0.57
    ה
    0.56
    자가
    0.56
    IS
    0.55
    POSITIVE LOGITS
    ated
    0.62
    ati
    0.61
    ades
    0.60
    át
    0.60
    ating
    0.58
    uri
    0.58
    ți
    0.58
    ada
    0.57
    asionally
    0.57
    uted
    0.57
    Activations Density 0.831%

    No Known Activations