© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5552
    Prev
    Next
    INDEX
    Explanations

    future expectations and challenges

    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
    umoto
    1.16
     vro
    1.09
    竟然
    1.09
    明明
    1.07
     lately
    1.02
    居然
    1.00
     preventable
    1.00
    !:
    0.99
    hutang
    0.99
    得了
    0.99
    POSITIVE LOGITS
     корректи
    2.17
     prosegu
    2.11
     дальней
    2.10
     tiếp
    2.02
     clarifications
    2.01
     weiteren
    2.01
     finalised
    1.98
     Gespr
    1.96
     weitere
    1.94
    Detailed
    1.93
    Activations Density 0.080%

    No Known Activations