© 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. 156602
    Prev
    Next
    INDEX
    Explanations

    possessive suffixes after words

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

    nationwide auction; accidental

    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
     Bless
    0.45
     strolled
    0.44
    spired
    0.44
     Klasse
    0.43
     Chesapeake
    0.43
    </b>
    0.43
    spiration
    0.42
     Fraser
    0.42
    ular
    0.41
    游
    0.41
    POSITIVE LOGITS
     reservas
    0.50
     escuelas
    0.49
    failures
    0.48
     aqui
    0.47
     बहुत
    0.46
     trigo
    0.46
    рын
    0.46
    ຕ່
    0.46
     నాలు
    0.46
     asociaciones
    0.46
    Activations Density 0.001%

    No Known Activations