© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4664
    Prev
    Next
    INDEX
    Explanations

    introducing definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     elastic
    1.21
     grasses
    1.19
     없
    1.14
     dandelion
    1.14
     noun
    1.12
     hunk
    1.09
    $.)
    1.08
     小型
    1.06
    olids
    1.05
     large
    1.05
    POSITIVE LOGITS
     oppure
    1.43
     respectivement
    1.41
     respectivamente
    1.38
     sedangkan
    1.31
     Weiter
    1.28
     ergän
    1.28
     sowie
    1.27
     wobei
    1.27
     Consultado
    1.27
     ausführ
    1.26
    Activations Density 0.089%

    No Known Activations