© 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. 98854
    Prev
    Next
    INDEX
    Explanations

    naming specific entities with subsequent descriptors

    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
     those
    -1.11
    stuffs
    -0.94
     plenty
    -0.93
     precisely
    -0.90
     even
    -0.86
     दौरान
    -0.85
     precisamente
    -0.85
     purported
    -0.84
     trasfer
    -0.84
     wanted
    -0.84
    POSITIVE LOGITS
     Africans
    0.97
     Conversations
    0.96
    Conversations
    0.91
    ʼn
    0.90
    кож
    0.89
     learnings
    0.89
     sequins
    0.84
    enums
    0.84
     raving
    0.84
    ⎈
    0.83
    Activations Density 0.015%

    No Known Activations