© 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. 34-GEMMASCOPE-RES-131K
    7. 118961
    Prev
    Next
    INDEX
    Explanations

    affecting and causing harm

    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
     exigences
    -0.94
     triomphe
    -0.93
     granito
    -0.93
     dialami
    -0.92
     changements
    -0.91
     parcour
    -0.91
     rafra
    -0.90
     poissons
    -0.90
     entret
    -0.90
     alcool
    -0.89
    POSITIVE LOGITS
     causing
    3.13
    causing
    2.17
     impair
    2.11
     cause
    2.08
     causes
    2.02
     destabili
    1.99
     adversely
    1.95
     caused
    1.94
     affecting
    1.93
     negatively
    1.86
    Activations Density 0.399%

    No Known Activations