© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    protecting users from harm

    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
    หมาย
    1.33
    zyna
    1.18
     вышла
    1.15
    izacji
    1.12
     ponownie
    1.11
    再次
    1.11
    wi
    1.10
    仍
    1.10
    เสียหาย
    1.08
    ัพ
    1.08
    POSITIVE LOGITS
     minimalism
    1.22
     phrasing
    1.21
     ironic
    1.15
    こういう
    1.15
    সই
    1.11
     konsep
    1.10
     typography
    1.10
     minimalist
    1.10
     aesthetics
    1.08
     teilen
    1.05
    Activations Density 0.841%

    No Known Activations