© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7183
    Prev
    Next
    INDEX
    Explanations

    biblical or religious references

    np_acts-logits-general · gemini-2.5-flash-lite

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    =@@
    0.41
    ierls
    0.38
    ოვანი
    0.38
     centaines
    0.38
     esp
    0.36
     ouvido
    0.36
    几十
    0.35
    嵬
    0.35
     hundreds
    0.35
     aja
    0.35
    POSITIVE LOGITS
    Blessed
    0.39
     Lenz
    0.38
     Blessed
    0.38
    lhs
    0.37
     Armor
    0.35
     nein
    0.35
     Nel
    0.34
    Nel
    0.34
    atkar
    0.34
     blessed
    0.34
    Activations Density 0.202%

    No Known Activations