© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 38440
    Prev
    Next
    INDEX
    Explanations

    noun followed by a preposition or verb

    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_31_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
     CHICAGO
    0.41
    -
    0.40
     “
    0.38
    ované
    0.38
     Scandinavia
    0.37
     Rooster
    0.37
     或
    0.37
     KLE
    0.36
     U
    0.36
     (“
    0.36
    POSITIVE LOGITS
    .~\
    0.39
    ~\
    0.38
    झ
    0.38
    अ
    0.35
    ಸ್ಥ
    0.35
     څرنګ
    0.35
    ܀
    0.35
    rieben
    0.35
    amorph
    0.34
    ПР
    0.34
    Activations Density 0.134%

    No Known Activations