© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3699
    Prev
    Next
    INDEX
    Explanations

    results or outcomes observed

    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_7_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
     Patterson
    1.29
    娅
    1.23
     PP
    1.18
     McCr
    1.15
    ร์
    1.15
    픕
    1.12
     Mp
    1.11
    ็
    1.10
    ้าร
    1.08
     Orton
    1.08
    POSITIVE LOGITS
    hotel
    1.19
     semaphore
    1.17
     fluvial
    1.17
    adaptive
    1.15
    behaviour
    1.13
     optimise
    1.12
     semiconductor
    1.10
     behavioural
    1.10
    hydrogen
    1.09
     humour
    1.09
    Activations Density 0.306%

    No Known Activations