© 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-65K
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    foreign and abstract concepts

    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
     suboptimal
    0.34
    '
    0.31
     estás
    0.30
    ут
    0.30
    a
    0.30
     egregious
    0.29
     onboarding
    0.29
     unsurprisingly
    0.29
     afield
    0.29
    ል
    0.29
    POSITIVE LOGITS
     téléphone
    0.31
     دارو
    0.29
     کی
    0.28
     droits
    0.28
     devlet
    0.28
     âge
    0.28
     गिनती
    0.27
     médicaments
    0.27
     ජී
    0.27
    <unused706>
    0.27
    Activations Density 0.130%

    No Known Activations