© 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. 5550
    Prev
    Next
    INDEX
    Explanations

    user-friendly interfaces

    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
     rimane
    1.01
     ebben
    0.85
    澱
    0.84
     poi
    0.84
    อกาส
    0.83
    在那里
    0.83
    Later
    0.83
     acog
    0.82
    ตี
    0.81
    了出来
    0.81
    POSITIVE LOGITS
    imore
    1.53
    اری
    1.50
    olium
    1.47
    Johann
    1.46
    }}_{
    1.45
    achi
    1.45
     compounded
    1.44
     delimited
    1.43
     thous
    1.42
    Affine
    1.42
    Activations Density 0.051%

    No Known Activations