© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50861
    Prev
    Next
    INDEX
    Explanations

    accidentally unhappy without

    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_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
    _{
    0.52
     ,
    0.43
    結局
    0.41
    }_{
    0.40
     legales
    0.39
    ierne
    0.39
    кие
    0.38
     fucking
    0.38
    enciones
    0.38
     افواج
    0.38
    POSITIVE LOGITS
    㖑
    0.55
    原来的
    0.49
    遌
    0.48
     autrefois
    0.48
    κά
    0.46
     auparavant
    0.44
     এমন
    0.41
    掝
    0.41
    মিক্যাল
    0.41
     aj
    0.40
    Activations Density 0.011%

    No Known Activations