© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9167
    Prev
    Next
    INDEX
    Explanations

    contacting professionals or services

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that urge immediate action or contacting someone (calls to call, contact, talk to, ask, document, or seek help).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
     erreurs
    0.40
     Wikiseite
    0.37
     घटनाएं
    0.37
    ája
    0.36
     errors
    0.36
    帧
    0.36
     erros
    0.36
    が発生
    0.35
    烬
    0.35
    錯誤
    0.35
    POSITIVE LOGITS
     dokter
    0.59
     authorities
    0.56
     pharmacist
    0.54
     doctor
    0.54
     consult
    0.52
     advisor
    0.52
    相談
    0.52
     solicitor
    0.52
     solicitors
    0.52
     menghubungi
    0.51
    Activations Density 0.114%

    No Known Activations