© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3351
    Prev
    Next
    INDEX
    Explanations

    import statement context

    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_12_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
     boat
    1.34
    -
    1.33
     born
    1.21
     balloon
    1.20
     put
    1.18
    he
    1.15
    w
    1.10
     g
    1.09
     |
    1.09
    -,
    1.09
    POSITIVE LOGITS
    mobili
    2.24
     살펴보도록
    2.17
     prá
    2.16
     depositphotos
    2.13
    WhiteElo
    2.11
    perties
    2.09
     chiế
    2.08
     Gerardo
    2.07
     içeren
    2.06
    Reprodu
    2.06
    Activations Density 0.001%

    No Known Activations