© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29956
    Prev
    Next
    INDEX
    Explanations

    potential for life

    np_acts-logits-general · gemini-2.5-flash-lite

    potential for liquid water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Franco
    0.47
     Kriegs
    0.42
    ኰ
    0.41
    Alien
    0.39
    Franc
    0.39
     planeta
    0.38
    Geometric
    0.38
    Monte
    0.38
    իմ
    0.38
     Franc
    0.38
    POSITIVE LOGITS
    糗
    0.49
     potencial
    0.49
     potentiel
    0.43
     ireland
    0.43
     потен
    0.42
    潜在
    0.41
    realpath
    0.41
    ആര്‍
    0.40
     потенциа
    0.40
    ంటున్నారు
    0.39
    Activations Density 0.008%

    No Known Activations