© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82731
    Prev
    Next
    INDEX
    Explanations

    negative emotions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_width_262k_l0_small_affine
    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
    無理
    0.38
     thoracique
    0.38
    닝
    0.37
     বাঙ্গ
    0.36
    }^
    0.36
    olato
    0.35
    UEZ
    0.35
    JobID
    0.35
    }@
    0.35
    won
    0.35
    POSITIVE LOGITS
     lug
    0.77
     sinist
    0.77
     inquiet
    0.74
    inqu
    0.74
     мото
    0.72
     sinistra
    0.71
     menyer
    0.70
     dě
    0.67
     sinister
    0.65
     ж
    0.64
    Activations Density 0.022%

    No Known Activations