© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57753
    Prev
    Next
    INDEX
    Explanations

    general opinions of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atization
    -1.18
     βιβ
    -1.13
    Hvordan
    -1.12
    ’
    -1.12
    توضیحات
    -1.11
    щены
    -1.10
    Datepicker
    -1.10
    และ
    -1.09
    PENDAHULUAN
    -1.09
     ambassade
    -1.08
    POSITIVE LOGITS
     says
    2.05
     think
    1.88
     say
    1.86
     said
    1.79
     always
    1.73
     like
    1.70
     often
    1.62
     will
    1.55
     thinks
    1.53
     should
    1.52
    Activations Density 0.028%

    No Known Activations