© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38457
    Prev
    Next
    INDEX
    Explanations

    post hoc, posthumous, Op. number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zędu
    -0.81
     hashlib
    -0.70
     פני
    -0.67
    owników
    -0.67
    宴
    -0.67
    ≲
    -0.67
    Hiring
    -0.66
     inundated
    -0.64
     сосу
    -0.63
    pew
    -0.62
    POSITIVE LOGITS
     posthum
    6.16
     pos
    3.53
    pos
    3.20
     Pos
    3.16
    Pos
    2.95
     пос
    2.95
     post
    2.48
     pó
    2.36
    POS
    2.11
     POS
    2.09
    Activations Density 0.086%

    No Known Activations