© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12212
    Prev
    Next
    INDEX
    Explanations

    complete without

    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
     instead
    -1.05
    camento
    -0.90
     rather
    -0.88
     CURLOPT
    -0.85
     directly
    -0.85
     Strukturen
    -0.85
     größe
    -0.84
    袄
    -0.84
     invece
    -0.84
     like
    -0.83
    POSITIVE LOGITS
    Without
    1.11
     must
    1.09
     obligatory
    0.98
     обязательно
    0.97
     olmaz
    0.96
     without
    0.95
     بدون
    0.95
     Without
    0.94
     обяза
    0.94
    やっぱり
    0.92
    Activations Density 0.034%

    No Known Activations