© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6555
    Prev
    Next
    INDEX
    Explanations

    expressing requirements or desires

    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
    Not in Any Lists

    No Comments

    Negative Logits
    type
    0.22
    ୟ
    0.21
    r
    0.20
              
    0.20
    <0xE2>
    0.20
     or
    0.20
    oretically
    0.20
    ↵
    0.20
     whose
    0.20
    och
    0.19
    POSITIVE LOGITS
     να
    0.43
     it
    0.35
     assurance
    0.35
     assurances
    0.34
     увидеть
    0.33
     să
    0.33
     услы
    0.32
     видеть
    0.32
     something
    0.31
     быть
    0.31
    Activations Density 0.036%

    No Known Activations