© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7774
    Prev
    Next
    INDEX
    Explanations

    'post' prefix noun compounds

    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_16k_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
    2
    0.65
    rok
    0.62
    fe
    0.60
    ah
    0.59
    g
    0.58
    the
    0.56
    arts
    0.56
    р
    0.55
    ab
    0.54
    bi
    0.54
    POSITIVE LOGITS
     post
    1.49
     пост
    1.23
     Post
    1.17
    post
    1.11
     पोस्ट
    1.11
    Post
    1.06
     পোষ্ট
    1.05
     پست
    1.04
     POST
    1.03
     postId
    1.00
    Activations Density 0.097%

    No Known Activations