© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69978
    Prev
    Next
    INDEX
    Explanations

    clustering, hierarchical, DBSCAN, SVM, PCA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $\$
    1.51
     saving
    1.44
     lira
    1.42
     screening
    1.40
    Cucumber
    1.40
     profitability
    1.39
    saving
    1.37
    cutting
    1.36
    isone
    1.36
    braska
    1.36
    POSITIVE LOGITS
    식
    1.10
    ouve
    1.07
     gł
    1.03
     nodo
    0.98
    棕
    0.98
    ้าร
    0.95
    VEMENT
    0.93
     labyr
    0.92
     Chakraborty
    0.92
    Claud
    0.91
    Activations Density 0.004%

    No Known Activations