© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines and support resources

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     biomark
    0.49
     ornamentation
    0.48
     ornamented
    0.43
     analysing
    0.42
     touristic
    0.42
     interaction
    0.42
     monomial
    0.42
    iccation
    0.41
    🍡
    0.41
     stationery
    0.40
    POSITIVE LOGITS
     hotline
    0.87
     Hotline
    0.81
     Helpline
    0.75
     helpline
    0.72
     हेल्पलाइन
    0.71
     ACLU
    0.70
     NAACP
    0.69
     National
    0.64
     Emergency
    0.64
     FBI
    0.60
    Activations Density 0.048%

    No Known Activations