© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3370
    Prev
    Next
    INDEX
    Explanations

    thermal and temperature

    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
     Cellular
    -0.78
    ينا
    -0.73
    piano
    -0.70
    ڻ
    -0.67
    普
    -0.66
     perm
    -0.66
     terraza
    -0.66
     Brood
    -0.65
     talked
    -0.65
    ENCIÓN
    -0.65
    POSITIVE LOGITS
     detalle
    0.88
    complexity
    0.84
    TokenNameRBRACE
    0.81
     degenerative
    0.78
     tafel
    0.77
    @^
    0.77
     控制
    0.76
    ctrl
    0.74
     témo
    0.74
    térature
    0.74
    Activations Density 0.017%

    No Known Activations