© 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. 93445
    Prev
    Next
    INDEX
    Explanations

    Joint accreditation

    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
    ifique
    -0.80
     גב
    -0.73
    wins
    -0.72
    ][/
    -0.71
    ätter
    -0.70
    antas
    -0.70
    amines
    -0.69
     PRECISION
    -0.69
    <0xBC>
    -0.69
    heids
    -0.69
    POSITIVE LOGITS
     accreditation
    1.99
     Joint
    1.90
     Accreditation
    1.71
    Joint
    1.45
    Accreditation
    1.42
     accredit
    1.36
     accredited
    1.32
     JAC
    1.12
     JC
    1.05
     Magnet
    1.01
    Activations Density 0.048%

    No Known Activations