© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110583
    Prev
    Next
    INDEX
    Explanations

    assignments with unpacked variables

    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
    especially
    -1.51
     especialmente
    -1.46
    particularly
    -1.35
     soprattutto
    -1.28
    ↵
    -1.17
     особенно
    -1.11
     verschillende
    -1.09
    despite
    -1.08
     principalmente
    -1.07
     terutama
    -1.05
    POSITIVE LOGITS
     _,
    2.03
    _=
    1.42
    _,
    1.38
     _
    1.27
     *_
    1.24
     _)
    1.23
    (_,
    1.20
     new
    1.15
    __,
    1.15
     edgy
    1.14
    Activations Density 0.004%

    No Known Activations