© 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. 14229
    Prev
    Next
    INDEX
    Explanations

    floating with context

    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
     coupled
    2.84
    american
    2.70
    CMAKE
    2.50
    ceso
    2.45
    ெ
    2.44
     unacceptable
    2.42
     WrestleMania
    2.42
    稔
    2.41
    דור
    2.40
    ગવાન
    2.38
    POSITIVE LOGITS
    ة
    2.55
     widz
    2.17
    ulu
    2.17
    Literal
    2.11
     sıra
    2.11
     αι
    2.10
    ائل
    2.09
    Osm
    2.09
     einsch
    2.08
    魎
    2.07
    Activations Density 0.010%

    No Known Activations