© 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. 78185
    Prev
    Next
    INDEX
    Explanations

    tactile sensations and physical properties

    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
     دیده
    -0.85
    utkan
    -0.77
    了一口
    -0.77
    oise
    -0.76
    mbic
    -0.74
    ╭
    -0.73
     arkas
    -0.72
     retor
    -0.71
     jaw
    -0.71
    vod
    -0.70
    POSITIVE LOGITS
     tactile
    3.09
     feel
    2.88
     touch
    2.61
     texture
    2.42
     feels
    2.22
    feel
    2.16
     textures
    2.14
     Feel
    2.13
    Feel
    2.09
     FEEL
    2.08
    Activations Density 0.064%

    No Known Activations