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. 7743
    Prev
    Next
    INDEX
    Explanations

    elif and elseif statements

    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
     öt
    -1.22
    趼
    -1.20
    besondere
    -1.20
     meleg
    -1.09
    helfen
    -1.09
    ųjų
    -1.09
    Ayrıca
    -1.08
    İyi
    -1.08
     adresu
    -1.08
     ориги
    -1.08
    POSITIVE LOGITS
     dagegen
    1.20
     instead
    1.18
     things
    1.14
     partecipanti
    1.12
    re
    1.11
    」「
    1.10
    ʼ
    1.09
     molti
    1.06
     наоборот
    1.06
    ut
    1.05
    Activations Density 0.001%

    No Known Activations