© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    pipe delimiters

    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
     Chaud
    1.19
    函
    1.18
     Choud
    1.10
     холо
    1.08
     McIntyre
    1.08
     Quinn
    1.05
     Pierce
    1.04
     THOM
    1.03
     Doherty
    1.02
     Chr
    1.01
    POSITIVE LOGITS
     $|
    1.52
    |
    1.43
     |
    1.42
    |=|
    1.27
    }}|
    1.25
    :|
    1.25
    ,|
    1.24
    .|
    1.23
    }|
    1.23
     |.
    1.20
    Activations Density 0.976%

    No Known Activations