© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84768
    Prev
    Next
    INDEX
    Explanations

    bare minimum

    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
    راعة
    -0.75
     precede
    -0.75
    Demografie
    -0.75
     detalladas
    -0.75
    もし
    -0.74
    🟦
    -0.73
     लाख
    -0.72
    𝙐
    -0.72
    roscope
    -0.72
    entier
    -0.71
    POSITIVE LOGITS
     minimum
    4.84
     bare
    4.66
     minimal
    4.00
    minimum
    3.97
    Minimum
    3.63
    MINIMUM
    3.44
    minimal
    3.38
     Minimum
    3.33
     MINIMUM
    3.30
    bare
    3.27
    Activations Density 0.077%

    No Known Activations