© 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. 119501
    Prev
    Next
    INDEX
    Explanations

    special characters and non-english words

    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
    的目的
    0.40
     نیوز
    0.39
    េះ
    0.39
     permissive
    0.36
    }°
    0.36
    を開催
    0.36
     intersects
    0.35
     INITIAL
    0.35
     दुरुपयोग
    0.35
     olimp
    0.34
    POSITIVE LOGITS
    ቶ
    0.40
    娓
    0.38
    gladbach
    0.37
    Mart
    0.37
    विजय
    0.37
     আওয়ামীলীগের
    0.35
    allclasses
    0.35
     संक्रमण
    0.35
     المم
    0.35
     Viitattu
    0.35
    Activations Density 0.000%

    No Known Activations