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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3076
    Prev
    Next
    INDEX
    Explanations

    possessive nouns followed by concepts

    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
    ,
    0.40
    uje
    0.39
    ikiem
    0.38
    uen
    0.38
    ups
    0.38
    of
    0.37
    ides
    0.36
    wa
    0.36
    ę
    0.36
    se
    0.35
    POSITIVE LOGITS
    。
    0.37
    的能力
    0.34
    א
    0.34
    IAN
    0.33
     glycol
    0.33
     chimique
    0.32
     skupiny
    0.32
     contrats
    0.31
     przetwarz
    0.31
     odour
    0.31
    Activations Density 0.529%

    No Known Activations