© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1827
    Prev
    Next
    INDEX
    Explanations

    code snippets and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    onomie
    1.95
    ))).
    1.89
    »:
    1.87
    ”!
    1.87
    一来
    1.82
    "!
    1.81
     '.
    1.80
    ».
    1.77
     speakers
    1.75
    }}},
    1.74
    POSITIVE LOGITS
     Disha
    0.65
    ponente
    0.61
     Bhuv
    0.60
    賄
    0.59
    */)
    0.58
     Giulia
    0.57
     eTo
    0.56
     mv
    0.54
     DataFrame
    0.54
     nascost
    0.52
    Activations Density 0.013%

    No Known Activations