Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8750
    Prev
    Next
    INDEX
    Explanations

    years

    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
     but
    -1.55
    Generally
    -1.43
    渽
    -1.38
     without
    -1.38
     palsu
    -1.36
    癀
    -1.29
     they
    -1.29
     with
    -1.26
    There
    -1.25
     particularly
    -1.24
    POSITIVE LOGITS
     dessa
    1.19
     недавно
    1.18
     tých
    1.17
     harika
    1.12
     aynı
    1.09
     amd
    1.08
     heureuse
    1.08
     COVID
    1.05
    ne
    1.05
     Covid
    1.05
    Activations Density 0.217%

    No Known Activations