© 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. 2045
    Prev
    Next
    INDEX
    Explanations

    names and specific details

    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
     dacă
    0.50
     larg
    0.48
     poss
    0.45
     câ
    0.45
     ساي
    0.44
    ة
    0.43
          
    0.43
     ħ
    0.43
     substance
    0.42
     déchets
    0.42
    POSITIVE LOGITS
    JAMES
    0.51
    james
    0.51
    Maj
    0.50
     JAMES
    0.49
    Aplic
    0.49
     गोविंद
    0.48
    maktan
    0.48
    James
    0.48
    дами
    0.48
     james
    0.48
    Activations Density 0.000%

    No Known Activations