© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7171
    Prev
    Next
    INDEX
    Explanations

    look for

    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
    Negative Logits
     gevolg
    1.59
    bersihan
    1.59
    intai
    1.53
    obedience
    1.46
     appartenant
    1.44
    یکا
    1.44
    ínas
    1.42
    ]]=
    1.40
     muž
    1.37
    人は
    1.37
    POSITIVE LOGITS
     multiplying
    2.23
     multiplication
    2.12
     scenario
    2.11
     oven
    1.94
     nationwide
    1.90
     multiplied
    1.89
     multiplications
    1.88
    ็ง
    1.85
     Jihad
    1.85
     scenarios
    1.85
    Activations Density 0.025%

    No Known Activations