© 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. 77695
    Prev
    Next
    INDEX
    Explanations

    html anchor tags

    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
    езда
    -0.81
    fpath
    -0.79
     nữa
    -0.77
    Btns
    -0.74
     列
    -0.73
     heat
    -0.73
    Indication
    -0.71
     zodiaco
    -0.71
    lə
    -0.70
     tia
    -0.70
    POSITIVE LOGITS
     anchor
    1.28
    anchor
    1.28
    Anchor
    1.13
    ](#
    1.10
     anchors
    1.08
     bookmark
    1.06
    bookmark
    1.03
    锚
    1.03
    MARKER
    0.99
     Anchor
    0.96
    Activations Density 0.118%

    No Known Activations