© 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. 53-GEMMASCOPE-2-RES-262K
    7. 8811
    Prev
    Next
    INDEX
    Explanations

    pu 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_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
    紘
    0.46
    鐩
    0.45
    ၚ
    0.41
    ంబేద్
    0.41
     তেলেভ
    0.40
     jq
    0.40
    ంబే
    0.40
    ంబేద్కర్
    0.40
    睨
    0.39
    嗦
    0.39
    POSITIVE LOGITS
     пу
    2.94
     pu
    2.80
    Pu
    2.67
     Пу
    2.66
     PU
    2.64
     Pu
    2.63
    Пу
    2.58
    PU
    2.55
    pu
    2.50
     푸
    2.42
    Activations Density 0.080%

    No Known Activations