© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 7782
    Prev
    Next
    INDEX
    Explanations

    ```# followed by code, urls, or instructions```

    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_31_width_65k_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
     uptick
    0.69
     adipis
    0.63
     entitlements
    0.62
     ਆ
    0.61
     γλώ
    0.61
     extracurricular
    0.61
    а
    0.59
     упраж
    0.59
    ン
    0.58
     apparition
    0.58
    POSITIVE LOGITS
    ot
    1.17
    al
    1.15
    ed
    1.11
    ol
    1.05
    er
    1.04
    es
    0.98
    c
    0.97
    el
    0.93
    can
    0.93
    ca
    0.89
    Activations Density 0.041%

    No Known Activations