© 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. 76048
    Prev
    Next
    INDEX
    Explanations

    questions starting with what

    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
    Bakgrunns
    -1.18
     étan
    -1.18
    karena
    -1.16
    ufficient
    -1.12
     ymm
    -1.10
    lxt
    -1.09
     réfrig
    -1.05
     coûts
    -1.05
    lería
    -1.03
    引用元
    -1.03
    POSITIVE LOGITS
     exactly
    1.53
     could
    1.45
     all
    1.35
     actually
    1.33
     is
    1.23
     are
    1.22
     should
    1.20
     will
    1.20
     shall
    1.13
     had
    1.12
    Activations Density 0.045%

    No Known Activations