© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108921
    Prev
    Next
    INDEX
    Explanations

    melting and crystallization

    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
    usata
    -0.81
    唠
    -0.78
    зю
    -0.74
    ISupport
    -0.73
    zeta
    -0.71
    ffre
    -0.70
     habrían
    -0.69
     경우
    -0.68
    rolling
    -0.68
    デュー
    -0.68
    POSITIVE LOGITS
     recrystal
    1.08
     melt
    1.02
     melting
    0.97
     melts
    0.91
    Melting
    0.88
     Melt
    0.84
     decomposition
    0.82
    digm
    0.79
     Decomposition
    0.79
     decompose
    0.78
    Activations Density 0.004%

    No Known Activations