© 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. 22-GEMMASCOPE-RES-131K
    7. 12229
    Prev
    Next
    INDEX
    Explanations

    months and days

    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_22/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
     among
    -1.14
    celtic
    -1.09
     выращи
    -1.07
     kialak
    -1.06
     gewüns
    -1.06
    ムラ
    -1.05
    wholesome
    -1.04
    crocs
    -1.02
    hijab
    -1.02
     amongst
    -1.01
    POSITIVE LOGITS
     January
    1.52
     July
    1.34
     October
    1.24
     August
    1.22
     September
    1.20
     April
    1.15
     June
    1.13
    lenül
    1.13
     December
    1.12
     для
    1.10
    Activations Density 0.051%

    No Known Activations