© 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-262K
    7. 200303
    Prev
    Next
    INDEX
    Explanations

    delivery range

    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_262k_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
    SPT
    0.50
    STO
    0.48
    行う
    0.47
     είναι
    0.46
    akuza
    0.46
    
    0.45
    KL
    0.45
    UL
    0.44
     doğru
    0.44
    NHL
    0.44
    POSITIVE LOGITS
    ر
    0.50
     Milestone
    0.47
    م
    0.47
     colleagues
    0.46
     milestone
    0.45
     Quot
    0.45
     Tel
    0.45
     Reason
    0.44
     Complement
    0.43
    Tel
    0.43
    Activations Density 0.002%

    No Known Activations