© 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-16K
    7. 327
    Prev
    Next
    INDEX
    Explanations

    Google AI Blog links

    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_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
     Saif
    1.41
    udni
    1.38
    minimize
    1.37
    aaS
    1.35
    profit
    1.34
     sensibil
    1.33
    趋
    1.32
     dringend
    1.32
     certainement
    1.32
     wohl
    1.31
    POSITIVE LOGITS
     arcs
    1.53
     parts
    1.51
    顱
    1.46
     fuses
    1.44
    鹅
    1.44
     spaces
    1.43
     shutters
    1.43
     springs
    1.42
     meshes
    1.42
     specimens
    1.41
    Activations Density 0.000%

    No Known Activations