© 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. 109531
    Prev
    Next
    INDEX
    Explanations

    addresses with city and state/province

    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
    …
    0.41
    /
    0.40
    ป
    0.39
    AA
    0.36
    Conf
    0.35
    Solid
    0.35
    هان
    0.34
     godfather
    0.34
    ही
    0.34
    Stop
    0.34
    POSITIVE LOGITS
     Agricultura
    0.47
     Mapa
    0.46
     España
    0.45
     으로
    0.45
     മ
    0.44
     ಇ
    0.44
     Wala
    0.43
     Será
    0.43
     Bereich
    0.43
     Bahnhof
    0.42
    Activations Density 0.002%

    No Known Activations