© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96366
    Prev
    Next
    INDEX
    Explanations

    bronze medal

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

    commissioned, killed, body, cornerstone, synapse

    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
    Options
    0.49
     ceo
    0.49
     Habit
    0.46
     revenue
    0.46
    Option
    0.45
    InMillis
    0.45
     ganglia
    0.45
    吵
    0.44
    嫚
    0.44
    Landscape
    0.43
    POSITIVE LOGITS
    ước
    0.56
    ips
    0.53
    ocond
    0.51
     }=\
    0.51
    ás
    0.49
    ducting
    0.49
    }}(\
    0.49
    äter
    0.49
    ánico
    0.47
     nást
    0.47
    Activations Density 0.000%

    No Known Activations