© 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. 930
    Prev
    Next
    INDEX
    Explanations

    often followed by )

    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
    ])):
    1.57
     youthful
    1.49
    ")):
    1.45
    )):
    1.44
     diameter
    1.37
    ))$,
    1.35
    ']):
    1.35
     contests
    1.35
     younger
    1.34
    ]):
    1.33
    POSITIVE LOGITS
    hattis
    1.02
    +","+
    0.96
    udara
    0.95
    ibacter
    0.94
    ottam
    0.90
     scelto
    0.89
    Swami
    0.89
    ()+"
    0.87
    organisme
    0.87
    +"|
    0.87
    Activations Density 0.007%

    No Known Activations