© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15679
    Prev
    Next
    INDEX
    Explanations

    MPa, Surgery, Rome, Grey, cm-1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ("[
    1.07
    <unused534>
    1.06
     ʻ
    0.99
    vée
    0.98
    ἀ
    0.98
    <unused464>
    0.96
    ңуз
    0.96
    <unused2173>
    0.96
    <unused2188>
    0.95
    Vermont
    0.94
    POSITIVE LOGITS
     upto
    1.50
     Vs
    1.42
     :-
    1.38
     inbuilt
    1.33
     বাহিরে
    1.32
    :-
    1.32
     Và
    1.30
     Kindly
    1.30
     equipments
    1.27
    DataBase
    1.27
    Activations Density 0.005%

    No Known Activations