© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2358
    Prev
    Next
    INDEX
    Explanations

    specific entities or concepts

    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
     brutal
    1.54
     turmoil
    1.47
     南
    1.45
     bolster
    1.42
     judicial
    1.40
     草
    1.39
     thwart
    1.38
     expedite
    1.38
     loyal
    1.37
     discursive
    1.37
    POSITIVE LOGITS
     которых
    0.93
    pannt
    0.92
    oid
    0.88
    Зна
    0.88
    зна
    0.88
    ገባ
    0.87
     должно
    0.86
    _
    0.84
     algum
    0.84
    टीसी
    0.83
    Activations Density 0.051%

    No Known Activations