© 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. 7706
    Prev
    Next
    INDEX
    Explanations

    calculation results

    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
    Ր
    1.62
    さは
    1.53
     swipe
    1.52
    kontrol
    1.42
    뗀
    1.42
    тку
    1.41
    頼
    1.41
    encies
    1.41
    験
    1.38
    umbres
    1.37
    POSITIVE LOGITS
    Fifth
    1.23
    ชัย
    1.22
    йс
    1.18
     Bays
    1.18
    commut
    1.17
    Tags
    1.16
    itam
    1.12
    Fields
    1.11
    FIVE
    1.10
    Bald
    1.09
    Activations Density 0.098%

    No Known Activations