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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    crisis helpline services

    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_65k_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
     или
    0.45
    หรือ
    0.44
     或
    0.42
    PMorgan
    0.41
     or
    0.40
    または
    0.39
    或
    0.39
     或者
    0.39
     Skype
    0.39
    ходить
    0.39
    POSITIVE LOGITS
     neutralization
    0.45
     這個
    0.42
     spectroscopy
    0.41
    日英
    0.41
     þis
    0.40
     والط
    0.40
     costes
    0.40
     analyses
    0.40
     repeater
    0.39
     personalisation
    0.39
    Activations Density 0.132%

    No Known Activations