© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    vending machines

    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
    ו
    3.62
    ಿ
    3.31
    iagn
    2.97
    ิศ
    2.96
    sapp
    2.91
    t
    2.91
    ihilation
    2.89
    ி
    2.89
    iaxial
    2.88
    دق
    2.88
    POSITIVE LOGITS
    اً
    2.32
    asan
    2.25
    fläche
    2.18
    нда
    2.17
    aksi
    2.14
          
    2.12
    aron
    2.10
            
    2.10
         
    2.10
    اب
    2.08
    Activations Density 0.006%

    No Known Activations