© 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. 223355
    Prev
    Next
    INDEX
    Explanations

    places, cities, and locations

    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
     स्वयं
    0.40
    M
    0.39
    Mâ
    0.39
     Moot
    0.38
    楦
    0.38
    Bal
    0.37
     moot
    0.36
    IZA
    0.36
    buty
    0.36
    ውን
    0.36
    POSITIVE LOGITS
    ╰
    0.42
     lastly
    0.39
    తున్నాయి
    0.38
    unarod
    0.37
     TECHN
    0.37
     propri
    0.36
     infancy
    0.36
    ாத
    0.36
     flooded
    0.36
     thunderstorms
    0.36
    Activations Density 0.000%

    No Known Activations