© 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. 2055
    Prev
    Next
    INDEX
    Explanations

    harmful manipulative unethical assistance

    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
    шок
    1.26
    იღ
    1.19
     smelly
    1.11
    گن
    1.10
     upsets
    1.01
    esthetic
    0.99
    𝐸
    0.99
     :).
    0.99
     dripping
    0.99
     малень
    0.98
    POSITIVE LOGITS
     afirmou
    1.13
     Viet
    1.09
     Việt
    1.07
    Prés
    1.04
     évalu
    1.03
     Foster
    1.01
     trú
    1.01
     Prés
    1.00
     hỗ
    1.00
     présent
    1.00
    Activations Density 0.241%

    No Known Activations