© 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. 12-GEMMASCOPE-2-RES-65K
    7. 976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Central
    0.89
    殭
    0.87
     dedicated
    0.81
     homomorphisms
    0.77
    ものが
    0.76
    V
    0.76
    Central
    0.75
     emerging
    0.75
     merkezi
    0.74
    纂
    0.73
    POSITIVE LOGITS
     rebuke
    2.07
     apologizing
    2.03
     condesc
    2.02
     humili
    2.01
     scolded
    1.98
     scorn
    1.95
     refus
    1.90
     reprim
    1.90
     apology
    1.89
     insulting
    1.88
    Activations Density 1.218%

    No Known Activations