© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    require('fs')

    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
    sko
    -0.79
    future
    -0.75
    Bytes
    -0.74
    ﻝ
    -0.74
     Eber
    -0.74
    ozat
    -0.71
    flower
    -0.71
     थ
    -0.70
     FLOAT
    -0.70
    FLOAT
    -0.70
    POSITIVE LOGITS
     fs
    3.53
    fs
    3.02
     FS
    2.58
    FS
    2.42
     Fs
    2.39
    Fs
    2.27
     fontSize
    1.75
    fontSize
    1.51
     fontsize
    1.41
    FontSize
    1.37
    Activations Density 0.063%

    No Known Activations