© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38823
    Prev
    Next
    INDEX
    Explanations

    product capabilities

    np_acts-logits-general · gemini-2.5-flash-lite

    hidden instructions and unnecessary repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    栦
    0.57
     tinc
    0.50
    or
    0.49
    僟
    0.48
    賁
    0.48
    
    0.47
    }}=
    0.47
     つい
    0.47
    幵
    0.46
    眼鏡
    0.45
    POSITIVE LOGITS
     capabilities
    0.47
     quintessential
    0.46
     мощность
    0.46
     strengths
    0.45
     fidel
    0.45
     competencies
    0.45
     pivotal
    0.44
     hemodynamic
    0.44
    ,
    0.43
     pandemic
    0.42
    Activations Density 0.001%

    No Known Activations