© 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. 138127
    Prev
    Next
    INDEX
    Explanations

    exploded in/into

    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
     ఎలాంటి
    0.65
    }$
    0.63
    asses
    0.60
    淤
    0.60
     Climbing
    0.58
    ist
    0.58
     ক্ষতি
    0.57
     
    0.57
    他就
    0.56
    ால்
    0.55
    POSITIVE LOGITS
    la
    0.57
    tx
    0.56
    kannya
    0.56
    txt
    0.55
     pagination
    0.54
    tim
    0.52
    tembre
    0.52
    sen
    0.51
    size
    0.50
    Desde
    0.49
    Activations Density 0.002%

    No Known Activations