© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 793
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     LEED
    0.85
     econometric
    0.81
     }}(\
    0.77
     )}$
    0.75
    }},
    0.69
    bench
    0.69
    }.$$
    0.69
     distributional
    0.69
    )^{*}$
    0.69
    ).$$
    0.68
    POSITIVE LOGITS
     villains
    2.53
     villain
    2.46
     werewolf
    2.44
     betrayal
    2.37
     blackmail
    2.35
     kidnap
    2.33
     traitor
    2.32
     Poison
    2.30
     betray
    2.28
     Villain
    2.25
    Activations Density 1.627%

    No Known Activations