© 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. 22-GEMMASCOPE-RES-131K
    7. 25899
    Prev
    Next
    INDEX
    Explanations

    right to live and be

    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_22/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
     veldig
    -1.05
     rất
    -1.03
     only
    -1.00
    ugget
    -0.95
    esthes
    -0.95
     skrevet
    -0.94
     recherche
    -0.93
    大量的
    -0.92
     écrit
    -0.91
     very
    -0.90
    POSITIVE LOGITS
    おはよう
    1.13
     when
    1.13
     když
    1.06
     penjelasan
    1.02
    ământ
    1.00
     META
    1.00
     freely
    0.99
     their
    0.99
    rj
    0.98
    選擇
    0.97
    Activations Density 0.046%

    No Known Activations