© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138420
    Prev
    Next
    INDEX
    Explanations

    phrases about passive voice or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.74
    de
    0.61
    E
    0.58
    OM
    0.57
    OS
    0.56
    OFF
    0.56
    ON
    0.56
    RAP
    0.55
    A
    0.55
    EN
    0.53
    POSITIVE LOGITS
     attenzione
    0.59
     richiede
    0.59
     genießen
    0.56
     hospitales
    0.55
     difficultés
    0.55
     richiesta
    0.55
     aiuta
    0.55
     médicaments
    0.54
     Ceux
    0.54
     Niederlande
    0.54
    Activations Density 0.000%

    No Known Activations