© 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. 4705
    Prev
    Next
    INDEX
    Explanations

    phrases connected by "and"

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

    line and hue

    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
    |(
    0.43
    "></
    0.42
     |
    0.39
    !”.
    0.39
    )$.
    0.39
    !).
    0.39
    ).(
    0.37
    }(
    0.37
    }(\
    0.37
    ”).
    0.37
    POSITIVE LOGITS
     fury
    0.71
     glory
    0.66
     sundry
    0.61
     woe
    0.54
     brim
    0.54
     mortar
    0.52
     Glory
    0.52
     splendour
    0.51
    roses
    0.50
     behold
    0.50
    Activations Density 0.241%

    No Known Activations