© 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-65K
    7. 62762
    Prev
    Next
    INDEX
    Explanations

    words starting with post

    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_65k_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
    bi
    0.56
    2
    0.56
    rok
    0.55
    ری
    0.51
    ŷ
    0.51
    őr
    0.50
    fe
    0.50
    리
    0.50
    ah
    0.49
    ņ
    0.48
    POSITIVE LOGITS
     post
    1.51
     Post
    1.25
     пост
    1.23
    post
    1.18
    Post
    1.13
     पोस्ट
    1.13
     POST
    1.06
     پست
    1.05
     પોસ્ટ
    1.03
     পোষ্ট
    1.02
    Activations Density 0.026%

    No Known Activations