© 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. 63764
    Prev
    Next
    INDEX
    Explanations

    hexadecimal escapes like \x

    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
     pronunci
    -0.77
     podium
    -0.75
     with
    -0.74
    ポート
    -0.72
    prechpartner
    -0.71
    ứ
    -0.71
     without
    -0.71
     shook
    -0.69
    Submitted
    -0.68
    Garcia
    -0.67
    POSITIVE LOGITS
    Luft
    0.82
     löytyy
    0.81
     mümkün
    0.80
     défaite
    0.80
     BIBSYS
    0.79
     nieruch
    0.79
    8
    0.78
     bulunabilir
    0.78
     jeunesse
    0.76
     réc
    0.76
    Activations Density 0.014%

    No Known Activations