Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 166249
    Prev
    Next
    INDEX
    Explanations

    Unreal Engine

    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_53_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
    мила
    0.39
    Mall
    0.36
    magnet
    0.36
    حب
    0.36
    鱔
    0.36
    Pip
    0.35
     uwagę
    0.35
    こちら
    0.34
    auti
    0.34
    haps
    0.34
    POSITIVE LOGITS
     beat
    0.43
    倬
    0.43
     beats
    0.42
     Turned
    0.40
     Beat
    0.40
     agrícola
    0.39
     Kakkar
    0.39
     Terrain
    0.39
     Fighting
    0.39
     buk
    0.38
    Activations Density 0.004%

    No Known Activations