© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2872
    Prev
    Next
    INDEX
    Explanations

    pal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ELO
    0.65
    ETO
    0.64
    eto
    0.64
    정을
    0.62
    𝚓
    0.62
    TOK
    0.61
     jett
    0.60
     sech
    0.60
    ética
    0.59
     JT
    0.59
    POSITIVE LOGITS
    fa
    0.65
    cu
    0.61
    एमएस
    0.60
    masters
    0.60
    构
    0.59
    φων
    0.59
    cula
    0.57
     Sovereign
    0.56
     Cu
    0.55
    fp
    0.55
    Activations Density 0.233%

    No Known Activations