© 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. 78673
    Prev
    Next
    INDEX
    Explanations

    permission to obtain

    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
     you
    -1.70
     its
    -1.20
    以來
    -1.06
     modest
    -1.05
     員
    -1.00
     Very
    -0.94
     級
    -0.93
     allow
    -0.90
    Leírás
    -0.89
     visible
    -0.89
    POSITIVE LOGITS
     also
    1.05
    :''
    1.04
    entwick
    0.95
     secondes
    0.94
    says
    0.93
    ")));
    0.93
    selig
    0.92
    '%
    0.92
    isSet
    0.91
     ἀ
    0.89
    Activations Density 0.095%

    No Known Activations