© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66417
    Prev
    Next
    INDEX
    Explanations

    past actions and descriptions

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

    auxiliary verbs followed by verbs

    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_31_width_262k_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
    acariy
    0.48
    >∕</
    0.46
    𒂍
    0.44
    avacak
    0.43
    ూరు
    0.43
    氛围
    0.43
    歟
    0.43
    ovjek
    0.42
    십니까
    0.41
     मार्ग
    0.41
    POSITIVE LOGITS
    0.45
     thinks
    0.44
     \
    0.43
     +
    0.42
     responds
    0.41
    decl
    0.41
     spain
    0.41
     tricky
    0.41
    ])
    0.40
     ss
    0.40
    Activations Density 0.002%

    No Known Activations