© 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. 12276
    Prev
    Next
    INDEX
    Explanations

    if ... then .

    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
     and
    -1.37
     mok
    -1.20
     мог
    -1.14
     mauva
    -1.11
     westfalen
    -1.10
     simili
    -1.09
    注意事
    -1.09
     xadrez
    -1.06
     opini
    -1.05
     reputa
    -1.05
    POSITIVE LOGITS
     then
    1.99
     or
    1.88
     thì
    1.73
     Then
    1.38
     entonces
    1.36
     you
    1.27
     any
    1.20
     there
    1.19
     allora
    1.17
     alors
    1.16
    Activations Density 0.057%

    No Known Activations