© 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. 53-GEMMASCOPE-2-RES-262K
    4. 9177
    Prev
    Next
    INDEX
    Explanations

    referring to things above

    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
    preceq
    0.40
     млад
    0.39
    leqslant
    0.35
    rtimes
    0.35
    ស្ស
    0.34
    镛
    0.34
    หมือน
    0.33
     sott
    0.33
    ёз
    0.33
    ⎣
    0.33
    POSITIVE LOGITS
     above
    4.69
    above
    4.22
     Above
    4.13
    Above
    4.09
     acima
    3.83
     ABOVE
    3.70
     выше
    3.67
     فوق
    3.53
     boven
    3.45
     diatas
    3.22
    Activations Density 0.115%

    No Known Activations