© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    programming library imports

    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_65k_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
     staffing
    1.18
     tipping
    1.14
     in
    1.13
     exemplar
    1.01
     angst
    1.00
     perpetrators
    1.00
     transgress
    1.00
     a
    0.99
     people
    0.99
     factual
    0.98
    POSITIVE LOGITS
    Ско
    1.49
    ච
    1.43
    JsonObject
    1.41
    اللہ
    1.41
    ừa
    1.40
    अय
    1.38
     تعالیٰ
    1.37
    ىز
    1.37
    Json
    1.37
     सनातन
    1.36
    Activations Density 0.023%

    No Known Activations