© 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. 92897
    Prev
    Next
    INDEX
    Explanations

    code blocks with `do`

    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
     all
    -1.23
     has
    -1.23
     from
    -1.20
     by
    -1.16
     out
    -1.10
     ALL
    -1.04
    All
    -1.04
     including
    -1.02
     does
    -0.99
     one
    -0.98
    POSITIVE LOGITS
     repuesto
    1.24
     vacunas
    1.16
    蒽
    1.05
    gä
    1.05
     fuper
    1.05
    disambiguation
    1.05
    谖
    1.04
     سات
    1.03
    】：
    1.03
    そも
    1.02
    Activations Density 0.052%

    No Known Activations