© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1805
    Prev
    Next
    INDEX
    Explanations

    algorithm

    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
    es
    2.84
     gpointer
    2.70
    em
    2.55
    ască
    2.52
    ுகளில்
    2.49
    
    2.46
    emain
    2.45
    ektedir
    2.43
    ுக
    2.42
    DAG
    2.41
    POSITIVE LOGITS
    ing
    2.80
    ries
    2.58
    𝘁
    2.56
    𝘂
    2.55
    𝗳
    2.55
     resident
    2.48
    𝗺
    2.47
    .'"
    2.43
    '."
    2.41
    ,'"
    2.40
    Activations Density 0.062%

    No Known Activations